2-month plan: the standard path
Eight weeks on one capstone, an assistant that answers questions about your own documents, from the foundations through RAG, agents, evals and deployment to a portfolio case study and the job search. About 10 hours a week. The topics follow the learning path; other plans: 1-month plan · 3-month plan · 6-month plan.
An unofficial study plan built from the public posts of Bashiri Smith and Melvin Vivas, not affiliated with or endorsed by them. Items under Fill the gap are not from the creators: they cover skills their posts don't. Track your progress in the library app; ticks are saved in your browser.
Week 1: Roadmap and foundations
Goal Explain what AI engineers build and how neural networks and transformers work; scope your capstone with 25-30 test questions. (about 11 h in total)
Core
- The Complete AI Engineer Roadmap for 2026 (Exact Courses + Step-by-Step) · Video · youtube.com · the creator's own
Do: Whole video (30 min); note the five skill areas and which ones your current experience already covers · about 45 min. - 3Blue1Brown Neural Networks series · Video · youtube.com
Do: Chapters 1-3, 'Large Language Models explained briefly' and chapters 5-6 (about 1 h 55 min of video); chapter 4 (backprop calculus) and chapter 7 are optional. - How to Build a Coding Project That Will Get You Hired in 2026 [FULL BLUEPRINT] · Video · youtube.com · the creator's own
Do: Whole video (15 min); use its target-company and problem-research steps to choose your capstone's use case · about 30 min.
From the creators' posts
- The 3 Levels of AI Engineering: LLM Apps → Production → Agentic Systems · Bashiri Smith, Facebook · 1:13
- 3-Month Roadmap to AI Engineering for Experienced Software Engineers · Bashiri Smith, Facebook · 0:07
- Software Engineering Fundamentals Before AI Engineering · Bashiri Smith, Facebook · 0:49
- Apply While You Build: Get Job-Search Feedback on Your AI Project Early · Bashiri Smith, Facebook · 1:12
Build
- Capstone kickoff: pick one focused use case over documents you know (team runbooks, a product's docs or internal policies) and write a one-page brief plus 25-30 real questions with their expected answers and source pages. Then, without AI help, scaffold the repo as your fundamentals check: a small web API (FastAPI or similar) with a stub /ask endpoint, tests and CI. (about 5.5 h) Idea from 3-Month Roadmap to AI Engineering for Experienced Software Engineers.
Fill the gap (not from the creators)
- Pydantic docs: Models · Docs · pydantic.dev
Type-hinted models and validation underpin FastAPI, structured-output SDKs (OpenAI parse, Instructor) and agent frameworks, so this is the Python skill AI work leans on most. (about 1 h) - LLM Course: LLM Fundamentals (Maxime Labonne) · Course · github.com
The course's refresher on the maths, Python and neural networks behind LLMs. Its author suggests using it as a reference when needed rather than starting there. (about 15 min)
Optional
- 27 AI Engineering Projects to Get Hired - The Ultimate Guide · Video · youtube.com · the creator's own
- Neural Networks: Zero to Hero (Andrej Karpathy) · Course · karpathy.ai
Optional, to fill the gap (not from the creators)
- Stanford CME 295, Lecture 1: Transformers · Video · youtube.com
Free university lecture from Stanford Online (Autumn 2025, lecture 1 of 9): NLP background, tokenization, embeddings, word2vec, RNNs and LSTMs, then attention and the Transformer. (about 1.5 h)
Week 2: LLMs and prompting
Goal Explain tokens, context windows and LLM training, get reliable structured JSON from prompts, and call an LLM API from your service. (about 12 h in total)
Core
- [1hr Talk] Intro to Large Language Models (Andrej Karpathy) · Video · youtube.com
Do: Whole talk (1 h) · about 1.5 h. - ChatGPT Prompt Engineering for Developers · Course · deeplearning.ai
Do: All 9 lessons (about 1 h 40 min); run the notebooks and redo the JSON-output exercises on one of your own documents. - Prompting best practices (Claude Platform Docs) · Docs · platform.claude.com
Do: Read the guide and apply three of its techniques to your /ask system prompt · about 45 min.
From the creators' posts
- How to Relearn LLMs & RAG in 2026: A 7-Step Roadmap with Free Resources · Bashiri Smith, Facebook · 1:54
- Running Local Models for Agents: Tool Use, Context and Quantization · Melvin Vivas, X · 1:45
- Use HTML for LLM Outputs, Markdown for Context · Melvin Vivas, X
- Test models on your own workflow, not public benchmarks · Melvin Vivas, X
Build
- Capstone step 1, your first AI service: make /ask call an LLM API with a system prompt and one document in the context, return schema-validated JSON (answer, quoted source, confidence) and containerize the service with Docker. Log tokens and latency per call and compare two models on ten of your test questions. (about 5 h) Idea from AI Engineer Roadmap: Fundamentals, RAG, Agents, Books & Your First AI Service.
Fill the gap (not from the creators)
- Getting Structured LLM Output (DeepLearning.AI x .txt) · Course · deeplearning.ai
Vendor-neutral 1h21m course (updated Oct 2025) that moves from provider structured-output APIs with Pydantic to Instructor re-prompting and Outlines constrained decoding. Free with a DeepLearning.AI account during its platform beta. (about 2 h) - LLM Course: LLM Architecture (Maxime Labonne) · Course · github.com
How modern LLMs turn text into tokens, pass them through attention layers and generate text with different sampling strategies, with a short list of the best explainers. (about 15 min) - LLM Course: Running LLMs (Maxime Labonne) · Course · github.com
Using LLMs through APIs or running open models locally, plus prompt engineering and structuring outputs, with links to the tools for each. (about 15 min) - Phase 10: LLMs from Scratch (AI Engineering from Scratch, Rohit Ghumare) · Course · github.com
24 build-it-yourself lessons on how LLMs work, from tokenizers through pre-training and scaling. Skim the lesson list and bookmark the ones behind this week's topics. (about 15 min)
Optional
- OpenAI, Claude & Gemini API Tutorial in Python (Machine Learning Plus) · Article · machinelearningplus.com
- How GPT Works: From Token Embeddings to Multi-Head Attention · Melvin Vivas, X · 15:11
- Running LLMs Locally Without an Expensive Rig · Melvin Vivas, X
Optional, to fill the gap (not from the creators)
- Context Engineering (AI Engineering from Scratch, Rohit Ghumare) · Tutorial · github.com
A hands-on lesson: build a context assembler that budgets the window between instructions, retrieved documents, tools and conversation memory. (about 1.5 h) - Stanford CME 295, Lecture 2: Transformer-Based Models and Tricks · Video · youtube.com
Free university lecture from Stanford Online (Autumn 2025, lecture 2 of 9): attention variants (MHA, MQA, GQA), position embeddings and RoPE, and Transformer-based models such as BERT and its derivatives. (about 2 h) - Stanford CME 295, Lecture 3: Large Language Models · Video · youtube.com
Free university lecture from Stanford Online (Autumn 2025, lecture 3 of 9): what an LLM is, mixture of experts, context length, temperature, sampling, prompting, in-context learning, chain of thought and self-consistency. (about 2 h) - Stanford CME 295, Lecture 6: LLM Reasoning · Video · youtube.com
Free university lecture from Stanford Online (Autumn 2025, lecture 6 of 9): reasoning models, reinforcement learning for reasoning, GRPO and scaling. (about 2 h)
Week 3: Embeddings and vector search
Goal Explain embeddings and HNSW search, pick an embedding model by measuring recall on your data, and search your documents. (about 10 h in total)
Core
- Word Embedding and Word2Vec, Clearly Explained!!! (StatQuest with Josh Starmer) · Video · youtube.com
Do: Whole video (16 min) · about 30 min. - Vector Databases: from Embeddings to Applications (DeepLearning.AI) · Course · deeplearning.ai
Do: All 8 lessons (about 1 h 5 min), including HNSW, sparse/dense and hybrid search. - Sentence Transformers · Tool · sbert.net
Do: Quickstart and the semantic-search usage pages; use the library to embed your documents · about 45 min.
From the creators' posts
- How RAG Finds the Right Document Fast: Graph-Based Vector Search · Bashiri Smith, Facebook · 1:08
- AI Engineer Mistakes Pt. 3: Don't Grind Math First, Choose Embeddings Carefully · Bashiri Smith, Facebook · 0:31
- Fine-tuning all-MiniLM-L6-v2 to Beat OpenAI Embeddings · Melvin Vivas, X
- RAG vs CAG: Retrieval vs Cache Augmented Generation Explained · Bashiri Smith, Facebook · 1:31
Build
- Capstone step 2: chunk and embed all your documents into pgvector (or Chroma) with sentence-transformers and add a /search endpoint. Label the source of each test question and compare two embedding models (such as all-MiniLM-L6-v2 and a hosted API model) on recall@5; fine-tuning MiniLM on your domain is a stretch goal. (about 6.5 h) Idea from Fine-tuning all-MiniLM-L6-v2 to Beat OpenAI Embeddings.
Fill the gap (not from the creators)
- Step-by-Step Guide to Choosing the Best Embedding Model (Weaviate) · Article · weaviate.io
A 4-step process: define the use case, shortlist from MTEB by task, size, dimensions and max tokens, then build a small hand-labelled set (50-100 documents plus test queries) from your own data and compare models on precision and recall. (about 30 min)
Optional
- What is a Vector Database? Powering Semantic Search & AI Applications (IBM Technology) · Video · youtube.com
- Understanding and Applying Text Embeddings (DeepLearning.AI) · Course · deeplearning.ai
- pgvector · Tool · github.com
Week 4: RAG
Goal Build RAG that cites sources and abstains when unsure, then improve it with chunking, query rewriting, reranking and hybrid search. (about 10.5 h in total)
Core
- LangChain: RAG From Scratch (YouTube playlist) · Video · youtube.com
Do: Parts 1-9 (about 52 min: indexing, retrieval, generation and query translation: multi-query, RAG-Fusion, decomposition, step-back, HyDE), coding along with the notebooks in the rag-from-scratch repo. - Build Production-Ready Retrieval RAG Pipeline in LangChain | Hybrid Search (BM25), Re-ranking & HyDE (Venelin Valkov) · Video · youtube.com
Do: Whole video (15 min): hybrid BM25 + vector search, re-ranking and HyDE; code along · about 30 min. - How to become an expert in RAG (BASWE AI Engineer Field Guide) · PDF · drive.google.com · the creator's own
Do: One page; use its five stages as your checklist for weeks 4-7 · about 15 min.
From the creators' posts
- Basic RAG Pipeline in 60 Seconds: From Documents to Grounded Answers · Bashiri Smith, Facebook · 0:55
- RAG Chunking: Balancing Chunk Size for Precision and Context · Bashiri Smith, Facebook · 0:29
- Why Blind Top-K Retrieval Hurts RAG, and What to Use Instead · Bashiri Smith, Facebook · 1:11
- Fixing RAG Ranking Problems with a Cross-Encoder Re-ranker · Bashiri Smith, Facebook · 1:10
Build
- Capstone step 3: turn /ask into RAG that answers only from retrieved chunks, cites them and says 'I don't know' when nothing relevant comes back. Then compare blind top-5 against over-retrieve + cross-encoder re-rank + relevance threshold (add BM25 hybrid search if time allows) on your test questions. (about 6.5 h) Idea from Why Blind Top-K Retrieval Hurts RAG, and What to Use Instead.
Fill the gap (not from the creators)
- Contextual Retrieval (Anthropic Engineering) · Article · anthropic.com
Shows how adding LLM-generated context to each chunk before embedding and BM25 indexing, plus reranking, cut failed retrievals by up to 67%, with a runnable cookbook. (about 30 min) - LLM Course: RAG (Maxime Labonne) · Course · github.com
Orchestrators, retrievers, memory and evaluation for retrieval-augmented generation; the sections just before and after cover vector storage and advanced RAG. (about 15 min) - Phase 11: LLM Engineering (AI Engineering from Scratch, Rohit Ghumare) · Course · github.com
17 lessons on putting LLMs to work: prompt and context engineering, RAG, fine-tuning and evals. Skim the lesson list; the RAG lessons fit this week. (about 15 min)
Optional
- 5 Levels of Text Splitting for Retrieval (Greg Kamradt) · Video · youtube.com
- Advanced Retrieval for AI with Chroma (DeepLearning.AI) · Course · deeplearning.ai
- 3 Reasons a "Correct" RAG Pipeline Still Fails in Production · Bashiri Smith, Facebook · 1:03
Optional, to fill the gap (not from the creators)
- Advanced RAG (AI Engineering from Scratch, Rohit Ghumare) · Tutorial · github.com
A hands-on lesson: hybrid search that combines BM25 keyword matching with vector search, plus a cross-encoder reranker and better chunking. (about 1.5 h) - Production RAG with LangChain & Vector Databases (freeCodeCamp) · Course · youtube.com
Whole course: RAG from basics to production: debugging, hybrid search, observability, optimization, scaling, hosting and security. (about 7.5 h)
Week 5: Agents, tools and MCP
Goal Know when to use an agent or a fixed workflow, add tools with step limits and approval, and serve a tool over MCP. (about 10.5 h in total)
Core
- Hugging Face Agents Course · Course · huggingface.co
Do: Unit 1 (agent fundamentals: thought-action-observation, tools, building a first agent; the course budgets 3-4 h); Unit 2's LangGraph section only if you build with LangGraph · about 3.5 h. - Model Context Protocol (MCP) · Docs · modelcontextprotocol.io
Do: 'What is MCP', Architecture and the 'Build an MCP server' quickstart · about 1.5 h. - AI Agents vs AI Workflows: How to Choose for Production (AIBackends blog) · Article · aibackends.com · the creator's own
Do: Whole article (8-min read), including the hybrid pattern and decision checklist · about 15 min.
From the creators' posts
- 5 Agentic Design Patterns: ReAct, Planning, Reflection, Routing, Multi-Agent · Bashiri Smith, Facebook · 0:11
- LangChain vs. LangGraph Explained with One RAG Chatbot · Bashiri Smith, Facebook · 1:13
- Let agents run on their own and build an approval layer · Melvin Vivas, X
- 7 AI Engineering Concept Pairs: RAG vs Fine-Tuning, Agents vs Workflows & More · Bashiri Smith, Facebook · 1:47
Build
- Capstone step 4: make the assistant agentic with LangGraph or a plain tool-calling loop. Serve search_docs from a small MCP server, rewrite the query and retry once when results fall below your week-4 relevance threshold, cap the steps, and add one action tool (such as drafting a ticket or email) that waits for human approval before it runs. (about 4.5 h) Idea from LangChain vs. LangGraph Explained with One RAG Chatbot.
Fill the gap (not from the creators)
- Phase 13: Tools and Protocols (AI Engineering from Scratch, Rohit Ghumare) · Course · github.com
From function calling and tool schemas to MCP and other agent protocols, with security and governance. The phase page suggests shorter routes through its 45 lessons. (about 15 min) - Phase 14: Agent Engineering (AI Engineering from Scratch, Rohit Ghumare) · Course · github.com
Agents built from first principles, starting with the agent loop. The phase page lists two shorter routes if you do not need all of it. (about 15 min)
Optional
- What Are AI Agents? (IBM Technology) · Video · youtube.com
- Master All 20 Agentic Design Patterns (Mark Kashef) · Video · youtube.com
- BASWE: Agent Cheatsheet for AI Engineers · PDF · drive.google.com · the creator's own
Optional, to fill the gap (not from the creators)
- Build an MCP Server (AI Engineering from Scratch, Rohit Ghumare) · Tutorial · github.com
A hands-on lesson: the same stateless notes server built in Python and in TypeScript, using only the standard library for the protocol core. (about 1.5 h) - Stanford CME 295, Lecture 7: Agentic LLMs · Video · youtube.com
Free university lecture from Stanford Online (Autumn 2025, lecture 7 of 9): retrieval-augmented generation, advanced RAG techniques, function calling, agents and the ReAct framework. (about 2 h) - LangGraph Complete Course for Beginners (freeCodeCamp) · Course · youtube.com
Whole course: LangGraph state graphs built up over five practice graphs and four AI agents, ending with a RAG agent. (about 3 h) - Intro to MCP Servers: Model Context Protocol with Python (freeCodeCamp) · Course · youtube.com
Whole course: building and connecting MCP servers in Python. (about 1 h)
Week 6: Evals and guardrails
Goal Evaluate retrieval and answers separately with a golden set and an LLM judge, and guard against prompt injection, jailbreaks and PII leaks. (about 10.5 h in total)
Core
- Evaluation Field Guide (baswe.ai engineer accelerator – Ops and Evaluation module) · PDF · drive.google.com · the creator's own
Do: The fundamentals, LLM-as-a-judge, RAG-evaluation and production-evals sections (sections 01, 03, 04 and 07, about 17 of the 41 pages); keep the rest as reference. - promptfoo · Repo · github.com
Do: Getting-started setup plus one red-team (prompt-injection) scan against your /ask endpoint · about 1 h. - GliGuard Moderation Colab Notebook · Tool · colab.research.google.com · the creator's own
Do: Run the notebook end to end, then reuse its prompt and response screening in your service · about 30 min.
From the creators' posts
- How to Evaluate a RAG Pipeline: Retrieval vs. Generation (Interview Answer) · Bashiri Smith, Facebook · 2:23
- The 8 Layers of Evaluating Production RAG and Agent Systems · Bashiri Smith, Facebook · 0:07
- 5 Things AI Engineers Must Evaluate: RAG, Agents, Models, Data, Guardrails · Bashiri Smith, Facebook · 0:33
- Cautionary Tale: Claude Code Wiped a Production Database via Terraform · Melvin Vivas, X
Build
- Capstone step 5: grow your questions into a 30-50 case golden set (include unanswerable and prompt-injection cases) and score retrieval (precision/recall@k) and generation (faithfulness and correctness with an LLM judge) separately in promptfoo or pytest. Add input/output guardrails (PII redaction plus GliGuard prompt/response screening) and record baseline numbers. (about 5.5 h) Idea from How to Evaluate a RAG Pipeline: Retrieval vs. Generation (Interview Answer).
Fill the gap (not from the creators)
- The lethal trifecta for AI agents (Simon Willison) · Article · simonwillison.net
A 10-minute mental model of why an agent that has private data, untrusted content and an outbound channel can be hijacked to leak data, and why guardrail filters alone don't fix it. (about 15 min) - Your AI Product Needs Evals (Hamel Husain) · Article · hamel.dev
The standard first read: look at your data, write assertion-style unit tests, add human and LLM-judge review, and let evals drive iteration, all shown on a real product. (about 30 min) - LLM Course: Evaluation (Maxime Labonne) · Course · github.com
Automated benchmarks, human evaluation and model-based (LLM-as-judge) evaluation, and why a metric that becomes the target stops being a good measure. (about 15 min) - LLM Course: Securing LLMs (Maxime Labonne) · Course · github.com
LLM-specific weaknesses (prompt injection, data and prompt leaking, jailbreaks, backdoors) and how to defend against them with red teaming and guardrails. (about 15 min)
Optional
- Building Systems with the ChatGPT API · Course · deeplearning.ai
- RAGAS · Tool · github.com
- Detect PII and PHI with NVIDIA's GLiNER-PII Model · Melvin Vivas, X
Optional, to fill the gap (not from the creators)
- Stanford CME 295, Lecture 8: LLM Evaluation · Video · youtube.com
Free university lecture from Stanford Online (Autumn 2025, lecture 8 of 9): LLM-as-a-judge: how to use it well, its benefits, and its biases and pitfalls. (about 2 h) - RAG Evaluation Using DeepEval & Confident AI (Yash Patil) · Video · youtube.com
Whole video: measuring a RAG pipeline with DeepEval metrics and tracking results in Confident AI. (about 29 min) - Defending LLM: Prompt Injection (LiveOverflow) · Video · youtube.com
Whole video: why LLMs are inherently open to prompt injection, and the design choices that limit the damage: treating input as untrusted, prompt design, user isolation, narrow tasks, few-shot prompts, fine-tuning, input limits, temperature 0 and redundant checks. (about 17 min)
Week 7: Deploy, monitor, fine-tune
Goal Deploy the assistant in a container, trace latency and cost per request, and decide when fine-tuning beats RAG or prompting. (about 11.5 h in total)
Core
- FastAPI · Tool · fastapi.tiangolo.com
Do: Deployment section only: 'Deployment concepts' and 'FastAPI in Containers - Docker' · about 45 min. - Langfuse · Tool · langfuse.com
Do: Get-started tracing guide; trace one request end to end in your app · about 1 h. - Hugging Face LLM Course · Course · huggingface.co
Do: Chapter 11 only (chat templates, supervised fine-tuning, LoRA, evaluation); try the SFTTrainer + LoRA code on a small model in free Colab · about 2 h.
From the creators' posts
- Ollama vs vLLM: From Local AI Demo to Production Inference Serving · Bashiri Smith, Facebook · 0:45
- Taking a RAG App to Production: Evals, Guardrails, Cost and Tracing · Bashiri Smith, Facebook · 1:10
- How to Reduce Latency in a Production AI Agent (Interview Answer) · Bashiri Smith, Facebook · 1:22
- Choosing a Knowledge Strategy: RAG vs Graph vs Fine-Tuning vs CAG vs Long Context · Bashiri Smith, Facebook · 0:23
Build
- Capstone step 6: deploy the container to a free hosting tier, trace every request with Langfuse (retrieval, model and tool spans), log tokens, latency and cost per answer, and run the eval suite in CI as a gate before each deploy. Add one cost lever (prompt caching or routing easy questions to a smaller model) and report p95 latency and cost per answer before and after. (about 5.5 h) Idea from AI Engineer Roadmap for 2026 in 60 Seconds.
Fill the gap (not from the creators)
- Latency optimization guide (OpenAI API docs) · Docs · developers.openai.com
Seven provider-agnostic principles (process tokens faster, generate fewer tokens, use fewer input tokens, make fewer requests, parallelise, stream to cut perceived wait, don't default to an LLM) with a worked example. (about 30 min) - LLM Course: Pre-training (Maxime Labonne) · Course · github.com
How base models are pre-trained: data preparation, distributed training and scaling. Background, not a skill you need to use: it explains where the models you call or fine-tune come from. (about 15 min) - LLM Course: Supervised Fine-tuning (Maxime Labonne) · Course · github.com
Full fine-tuning compared with LoRA and QLoRA, the main training parameters, and the tools to run them; the next section covers preference alignment such as DPO. (about 15 min) - LLM Course: Deployment (Maxime Labonne) · Course · github.com
Ways to ship LLM apps, from local servers and demos to production servers and edge devices. (about 15 min) - LLM Course: Inference Optimization (Maxime Labonne) · Course · github.com
Flash Attention, the key-value cache and speculative decoding: the main ways to make generation faster and cheaper. (about 15 min) - Phase 17: Infrastructure and Production (AI Engineering from Scratch, Rohit Ghumare) · Course · github.com
Shipping LLM apps: managed platforms, model routing, gateways, monitoring and cost. Skim the lesson list and bookmark what your project needs. (about 15 min)
Optional
- donvito/notebooks · Repo · github.com · the creator's own
- Zero-Shot Prompt Routing with Liquid AI's LFM 2.5-Encoder-350M · Melvin Vivas, X · 2:16
- Large Language Model Operations (LLMOps) Explained (IBM Technology) · Video · youtube.com
Optional, to fill the gap (not from the creators)
- AI Gateways (AI Engineering from Scratch, Rohit Ghumare) · Tutorial · github.com
A lesson on gateways that sit between your app and model providers (LiteLLM, Portkey, Kong, Bifrost): routing, fallback, retries, rate limits and observability. (about 1 h) - Fine-Tuning with LoRA and QLoRA (AI Engineering from Scratch, Rohit Ghumare) · Tutorial · github.com
A hands-on lesson on why LoRA and QLoRA fit a 7B model in a few GB of memory, and how to set them up. (about 1.5 h) - Stanford CME 295, Lecture 4: LLM Training · Video · youtube.com
Free university lecture from Stanford Online (Autumn 2025, lecture 4 of 9): pre-training, quantization, hardware optimization, supervised fine-tuning (SFT) and LoRA. (about 2 h) - Stanford CME 295, Lecture 5: LLM Tuning · Video · youtube.com
Free university lecture from Stanford Online (Autumn 2025, lecture 5 of 9): preference tuning, RLHF, reward models, RL methods such as PPO, and DPO. (about 2 h) - Docker Tutorial for Beginners (TechWorld with Nana) · Course · youtube.com
Whole course: images, containers, Dockerfiles, Docker Compose, volumes and a full demo project. (about 3 h) - GitHub Actions Tutorial: CI/CD Pipeline with Docker (TechWorld with Nana) · Video · youtube.com
Whole video: workflows, events and jobs, and a CI pipeline that builds and pushes a Docker image. (about 32 min) - System Design Concepts Course and Interview Prep (freeCodeCamp) · Video · youtube.com
Whole video: core system design concepts: scaling, load balancing, caching, databases and APIs. (about 53 min)
Week 8: Design, portfolio, job search
Goal Walk through an AI system design with numbers and trade-offs, present your capstone as a case study, and run a targeted job search. (about 11 h in total)
Core
- Amazon Rufus (AI shopping assistant) · Article · amazon.science
Do: Read the write-up (5-min read) and redraw its architecture as a system-design exercise: custom LLM, retrieval over the catalogue, reviews and community Q&A, and how answers are streamed and checked · about 30 min. - 100 AI Engineering Interview Questions Guide · PDF · drive.google.com · the creator's own
Do: Skim all 100 questions, then answer 20 out loud across RAG, agents, ops/evals and safety, using numbers from your capstone · about 2 h. - The Interview Engine: The 7-Step System to Land AI Engineering Interviews · PDF · drive.google.com · the creator's own
Do: Work through steps 1-7: resume, tracker, referral mapping and the weekly outreach routine. The PDF has the prompts and email template; the tracker spreadsheet is only in the paid community, so make your own (Jobs, Warm paths, Contacts). The free resume template is linked from Bashiri's roadmap video · about 1.5 h.
From the creators' posts
- Production RAG Interview: Debugging Retrieval, Latency and Cost Like an Engineer · Bashiri Smith, Facebook · 1:47
- AI Engineer Interview Q&A: Graph RAG, Agent Memory, Observability, Guardrails · Bashiri Smith, Facebook · 1:32
- 6 Steps to Build a Resume Project That Lands an AI Engineering Job · Bashiri Smith, Facebook · 2:47
- 90-Day AI Engineering Job Search: Targeted Companies, Outreach & Loom Pitches · Bashiri Smith, Facebook · 1:29
Build
- Capstone step 7: publish it with a README (architecture diagram, eval results, p95 latency, cost per answer, trade-offs and known failure modes), a 3-minute Loom demo and a LinkedIn write-up. Then apply to 10 targeted roles using this week's tracker and outreach routine, pitching the capstone. (about 5.5 h) Idea from 7 Habits to Become an AI Engineer: Books, Tooling, Research & Shipping.
Fill the gap (not from the creators)
- Building A Generative AI Platform (Chip Huyen) · Article · huyenchip.com
A step-by-step reference architecture (context/RAG, guardrails, router and gateway, caching, write actions, observability, orchestration) that gives you the vocabulary design rounds expect. (about 1 h)
Optional
- Why Your Job Applications Keep Getting Ignored · Video · youtube.com · the creator's own
- Find Hidden AI Jobs: Search by Skills (RAG, LLMs), Not "AI Engineer" Titles · Bashiri Smith, Facebook · 1:03
- Bashiri Smith's AI Projects Guide · PDF · drive.google.com · the creator's own
Optional, to fill the gap (not from the creators)
- Project: Terminal Coding Agent (AI Engineering from Scratch, Rohit Ghumare) · Project · github.com
Capstone: build a terminal coding agent with a plan, a sandboxed tool surface and a loop that recovers from errors. A stretch project for after the plan. (about 35 h) - Project: Production RAG Chatbot (AI Engineering from Scratch, Rohit Ghumare) · Project · github.com
Capstone: a RAG chatbot for a regulated field, with hybrid search, reranking, citations and a golden-set, red-team and RAGAS evaluation. A stretch project for after the plan. (about 30 h) - Project: Multi-Agent Software Team (AI Engineering from Scratch, Rohit Ghumare) · Project · github.com
Capstone: an architect, parallel coders, a reviewer and a tester working as one team. A stretch project for after the plan. (about 40 h) - Project: GitHub Issue-to-PR Agent (AI Engineering from Scratch, Rohit Ghumare) · Project · github.com
Capstone: label an issue and get a tested pull request, built in a cloud sandbox with a minimal-permission GitHub App. A stretch project for after the plan. (about 30 h) - Project: MCP Server with Registry (AI Engineering from Scratch, Rohit Ghumare) · Project · github.com
Capstone: a stateless MCP server with tool discovery, a registry, authorization, policy and audit. A stretch project for after the plan. (about 25 h) - Stanford CME 295, Lecture 9: Recap and Current Trends · Video · youtube.com
Free university lecture from Stanford Online (Autumn 2025, lecture 9 of 9): a recap of the whole course and the topics trending now. (about 2 h) - Forward Deployed Engineering 101 (Kevin Bai, Anthropic, at AI Engineer) · Video · youtube.com
Whole video: the forward-deployed model as Palantir ran it: selling an outcome rather than a product or a service, the business case for large contracts, building on a reusable platform instead of one-off custom work, two questions to ask before starting, and what has changed now that building is agentic. (about 18 min)
Later
This plan leaves these topics for afterwards; they are all in the learning path: AI Dev Tools & Productivity; Industry Trends & Job Market.