SWE-to-AI Engineer Plan for 2027: LLMs, RAG, Agents, Evals, Job Search
Bashiri Smith · Facebook reel · 2026-10-02 · 0:07 · 13,430 views · Open on Facebook
Topics: Start Here: Roadmaps & Strategy, Resume, Job Search & Interviews, Evaluation (Evals) & Testing · Level: beginner
Summary
A short reel whose audio is only music. All the lessons are in the caption: a 7-step plan for software engineers moving into AI engineering going into 2027. You learn how LLMs work, build a RAG app and an agent, evaluate both, ship them as open source to real users, and turn the results into resume bullets and interview answers. It ends with job-search advice: search by skill keywords, not just job titles.
Key points
- Learn how LLMs work: tokens, embeddings, context windows, and when to use different models.
- Build a RAG app with hybrid search, reranking, and citations, and work out why it sometimes retrieves the wrong information.
- Build an agent that researches companies or updates a CRM, with retries and a human approval step.
- Evaluation is what separates a wannabe from a $200k AI engineer. Measure retrieval quality, answer accuracy, task success, latency, and cost for both projects.
- Open-source your projects and get real users. Fix what breaks and measure what improves.
- Write resume bullets that show the problem you solved, the tools you used, and the impact.
- Practice explaining your decisions in interviews: Why this model? Why RAG? What happens when a tool fails?
- Search by skill, not just title. The creator says over 50% of companies label AI job openings poorly. Try AI Engineer, Forward-Deployed Engineer, and AI Solutions Engineer, and also search keywords like RAG, RAGAS, Agents, LLM, and LangChain.
Resources mentioned
- The Complete AI Engineer Roadmap for 2026 (Exact Courses + Step-by-Step) · video · youtube.com · free
Bashiri Smith's free YouTube training on upgrading your skills and becoming competitive for AI engineering roles, with specific courses listed step by step.
Also in: Pointer to Bashiri Smith's Complete AI Engineer Roadmap for 2026 (Bashiri Smith on Facebook · notes), Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), Software Engineer to AI Engineer Before 2027: A 5-Step Career Plan (Bashiri Smith on Facebook · notes), 6 Free Videos to Move from Software Engineer to AI Engineer (Bashiri Smith on Facebook · notes) and 19 more - RAGAS · tool · github.com · free
Listed under RAG evaluation tools in the guide's evaluation stack.
Also in: Taking a RAG App to Production: Evals, Guardrails, Cost and Tracing (Bashiri Smith on Facebook · notes) - LangChain · tool · github.com · free · recommended by both Bashiri Smith & Melvin Vivas
Open-source framework with ready-made integrations and common interfaces for connecting LLMs, embedding models, vector stores and tools.
Also in: Basic RAG Pipeline in 60 Seconds: From Documents to Grounded Answers (Bashiri Smith on Facebook · notes), Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), LangChain vs. LangGraph Explained with One RAG Chatbot (Bashiri Smith on Facebook · notes), How to Relearn LLMs & RAG in 2026: A 7-Step Roadmap with Free Resources (Bashiri Smith on Facebook · notes) and 3 more
From the PDF shared here: The AI Pivot Field Guide
Open the original · 23 pages
A 2026 guide from the baswe.Ai Engineer Accelerator with three routes into AI engineering: mid-level software engineers (9 to 12 months), new grads (12 months) and non-technical domain experts who want to build agents (9 months). Its main idea is to build first. Start with LLM APIs and RAG, then agents, ops and evaluation, then safety, and leave ML math and foundations for last. It also covers job-market and salary data, portfolio and interview advice, and ends with a resource library of free and free-tier links. Pick your chapter, follow its steps in order, and use each step's 'Start here' links.
- Cursor · tool · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
AI-native code editor (VS Code with AI built in).
Also in: GLM 5.3 and GLM 5.3 Flash now in Cursor (Melvin Vivas on X · notes), Grok Bot Can Now Hand Off Coding Tasks to Cursor (Melvin Vivas on X · notes), Why Plan Mode Still Matters in AI Coding Assistants (Codex, Claude, Cursor) (Melvin Vivas on X · notes), Why Plan Mode Still Matters in AI Coding Agents (Codex, Claude, Cursor) (Melvin Vivas on X · notes) and 122 more - Claude Code · tool · code.claude.com · paid · recommended by both Bashiri Smith & Melvin Vivas
Build agents and pipelines from the terminal; the guide's main agentic coding tool.
Also in: Create Claude Code Plugins with /plugin-authoring (Melvin Vivas on X · notes), Claude Code mods: customize behavior and UI with plugins (Melvin Vivas on X · notes), AI Engineer Roadmap Overview: From ML Foundations to RAG, Agents & Ops (Bashiri Smith on Facebook · notes), SkillsBento: Free Plugin Marketplace for Codex and Claude Code (Melvin Vivas on X · notes) and 102 more - Google Colab · tool · colab.research.google.com · free · recommended by both Bashiri Smith & Melvin Vivas
Free GPU notebooks.
Also in: Run Notebooks on a Free GPU with Google Colab (T4, 15GB VRAM) (Melvin Vivas on X · notes), Run Local Models on a Free GPU with Google Colab (T4) (Melvin Vivas on X · notes), Free Colab Notebooks for Local Model Fine-Tuning and Inference (Melvin Vivas on X · notes), Intent classification for support using GLiNER2.5-Decide notebook (Melvin Vivas on X · notes) and 13 more - Vercel · tool · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
Deploy web apps and frontends.
Also in: OpenAI DevDay 2026 Recap: Dots, Agents API, Codex Cloud & Marketplace (Melvin Vivas on X · notes), 7 Habits to Become an AI Engineer: Books, Tooling, Research & Shipping (Bashiri Smith on Facebook · notes), Jev model added to the AIBackends API via Vercel AI Gateway (Melvin Vivas on X · notes), Open models now dominate token volume on Vercel AI Gateway (Melvin Vivas on X · notes) and 8 more - Docker · tool · docs.docker.com · free · recommended by both Bashiri Smith & Melvin Vivas
Containerize everything you ship.
Also in: Deploying AI workflow integrations with Apache Camel in Docker (Melvin Vivas on X · notes), Devin's cloud Ubuntu sandbox ships with Docker pre-installed (Melvin Vivas on X · notes), 7 Habits to Become an AI Engineer: Books, Tooling, Research & Shipping (Bashiri Smith on Facebook · notes), 8-Week Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes) and 6 more - OpenAI API · tool · platform.openai.com · paid · recommended by both Bashiri Smith & Melvin Vivas
OpenAI API documentation, including function calling and structured outputs.
Also in: How to Relearn LLMs & RAG in 2026: A 7-Step Roadmap with Free Resources (Bashiri Smith on Facebook · notes), Livestream: Building a React Native ChatGPT App with Cursor and OpenAI (Melvin Vivas on X · notes), GPT-Live-1: OpenAI's Full-Duplex Voice Model for Voice Agents in the API (Melvin Vivas on X · notes), The 3 Levels of AI Engineering: LLM Apps → Production → Agentic Systems (Bashiri Smith on Facebook · notes) and 5 more - FastAPI · tool · fastapi.tiangolo.com · free
Wrap your models as real inference APIs.
Also in: Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), 8-Week Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), Software Engineer to AI Engineer: Job Boards, Stack, Projects and Learning Sites (Bashiri Smith on Facebook · notes), AI Engineer Roadmap for 2026 in 60 Seconds (Bashiri Smith on Facebook · notes) and 1 more - Pinecone · tool · pinecone.io · free
A managed, production vector database (free tier).
Also in: Basic RAG Pipeline in 60 Seconds: From Documents to Grounded Answers (Bashiri Smith on Facebook · notes), Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), How RAG Works: Chunking, Embedding, Vector Storage, and Retrieval (Bashiri Smith on Facebook · notes), How RAG Works Under the Hood: Chunking, Embedding, Storage, Retrieval (Bashiri Smith on Facebook · notes) and 1 more - DeepLearning.AI · website · deeplearning.ai · free
The gold-standard ML fundamentals course; you can audit it for free.
Also in: How to Relearn LLMs & RAG in 2026: A 7-Step Roadmap with Free Resources (Bashiri Smith on Facebook · notes), Software Engineer to AI Engineer: Job Boards, Stack, Projects and Learning Sites (Bashiri Smith on Facebook · notes), 90-Day Plan to Land an AI Engineering Job: Benchmark, Learn, Build (Bashiri Smith on Facebook · notes) - Hugging Face Spaces · tool · huggingface.co · free · recommended by both Bashiri Smith & Melvin Vivas
Deploy demos publicly for free so recruiters can see them.
Also in: Every Hugging Face Space Now Has AGENTS.md for Coding Agents (Melvin Vivas on X · notes), Calling Hugging Face Spaces from Claude Code as Agent Tools (Melvin Vivas on X · notes), Hugging Face Pro Spaces Credits for Image Generation (Melvin Vivas on X · notes) - LangSmith · tool · docs.smith.langchain.com · free
Tracing, logging and evals; also used to track cost and latency.
Also in: Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), 7 Habits to Become an AI Engineer: Books, Tooling, Research & Shipping (Bashiri Smith on Facebook · notes) - n8n · tool · n8n.io · free · recommended by both Bashiri Smith & Melvin Vivas
No-code workflow automation with AI nodes.
Also in: n8n vs Apache Camel for enterprise AI workflows (Melvin Vivas on X · notes), Deploying AI workflow integrations with Apache Camel in Docker (Melvin Vivas on X · notes), How Postiz Hit $145K MRR: Agent-First Positioning and Selling Outcomes (Melvin Vivas on X · notes) - RAGAS · tool · github.com · free
Listed under RAG evaluation tools in the guide's evaluation stack.
Also in: Taking a RAG App to Production: Evals, Guardrails, Cost and Tracing (Bashiri Smith on Facebook · notes) - DVC (Data Version Control) · tool · dvc.org · free · open in a browser to verify
Version your data like code.
Also in: Five Core AI Engineering Topic Areas: A Study Roadmap Checklist (Bashiri Smith on Facebook · notes), 17-Step AI Engineer Roadmap: From Basic RAG to Agents, Evals, LLMOps & Governance (Bashiri Smith on Facebook · notes) - Hugging Face Agents Course · course · huggingface.co · free
A free agents course with a real completion certificate.
Also in: AI Engineer Roadmap Before 2027: Fundamentals, RAG, Agents, Ops, Evals (Bashiri Smith on Facebook · notes), AI Engineer Roadmap: Fundamentals, RAG, Agents, Books & Your First AI Service (Bashiri Smith on Facebook · notes) - Hugging Face LLM Course · course · huggingface.co · free
Hands-on course on transformers, tokenizers and fine-tuning.
Also in: How to Relearn LLMs & RAG in 2026: A 7-Step Roadmap with Free Resources (Bashiri Smith on Facebook · notes), AI Engineer Roadmap for 2026 in 60 Seconds (Bashiri Smith on Facebook · notes) - Neural Networks: Zero to Hero (Andrej Karpathy) · course · karpathy.ai · free
Build GPT from scratch. The guide calls it the deepest free foundation.
Also in: AI Engineer Roadmap Before 2027: Fundamentals, RAG, Agents, Ops, Evals (Bashiri Smith on Facebook · notes), AI Engineer Roadmap: Fundamentals, RAG, Agents, Books & Your First AI Service (Bashiri Smith on Facebook · notes) - CrewAI · tool · crewai.com · free
A framework for role-based multi-agent teams.
Also in: 8-Week Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes) - GitHub Copilot · tool · github.com · check price · recommended by both Bashiri Smith & Melvin Vivas
One of the agentic coding tools the guide names as letting non-technical builders ship.
Also in: Opinion: Enterprises Pick GitHub Copilot, but Cursor Is Better (Melvin Vivas on X · notes) - MLflow · tool · mlflow.org · free
Experiment tracking and a model registry.
Also in: Five Core AI Engineering Topic Areas: A Study Roadmap Checklist (Bashiri Smith on Facebook · notes) - Unstructured · tool · unstructured.io · free
Document and data processing for building RAG over your domain documents.
Also in: Basic RAG Pipeline in 60 Seconds: From Documents to Grounded Answers (Bashiri Smith on Facebook · notes) - Adversarial Prompting (Prompt Engineering Guide) · article · promptingguide.ai · free
How to defend against prompt injection and jailbreaks. - AI Agents in LangGraph (DeepLearning.AI) · course · deeplearning.ai · free
Build an agent, then rebuild it in LangGraph. - Anthropic API docs · docs · docs.anthropic.com · free
Claude API reference. The guide also points to it for safety guidance. - Anthropic Courses · repo · github.com · free
Courses on API fundamentals, real-world prompting, tool use and evals. The guide also calls this the 'Anthropic evals course'. - Anthropic Prompt Engineering Interactive Tutorial · repo · github.com · free
Nine hands-on prompt engineering chapters with exercises. - Chroma · tool · trychroma.com · free
The easiest open-source vector database to start with. - DeepLearning.AI Short Courses · course · deeplearning.ai · free
Applied courses of 1 to 2 hours on RAG, agents, LangChain and LLMOps. - Evidently AI · tool · evidentlyai.com · free
Drift detection and monitoring. - FAISS · tool · faiss.ai · free
Fast local similarity search from Meta. - fast.ai, Practical Deep Learning for Coders · course · course.fast.ai · free
Build-first deep learning course: you train a model in lesson 1. - Google Machine Learning Crash Course · course · developers.google.com · free
About 15 hours, free, no signup. Its Fairness module is recommended as one of the best intros to bias in ML. - Hugging Face PEFT · docs · huggingface.co · free
LoRA and QLoRA fine-tuning. - Kaggle Learn · course · kaggle.com · free
Free micro-courses with certificates. - Kaggle Notebooks · tool · kaggle.com · free
Free weekly GPU hours for experiments, plus public notebooks to learn from. - LangChain docs · docs · docs.langchain.com · free
Docs for LangChain, which the guide calls the most common LLM app framework. - LangGraph docs · docs · docs.langchain.com · free
Docs for LangGraph: controllable, stateful, multi-agent orchestration. - LlamaIndex docs · docs · docs.llamaindex.ai · free
Docs for LlamaIndex, a data framework for RAG over your own documents. - Made With ML · course · madewithml.com · free
End-to-end MLOps curriculum; the guide calls it the best free resource in the category. - Make · tool · make.com · free · open in a browser to verify
Visual automation builder. - MLOps.community · community · mlops.com · free
Virtual AI meetups to attend while you build your network. The PDF's link points to MLOps.com, not mlops.community. - nanoGPT (Karpathy) · repo · github.com · free
A minimal, readable repo for training GPT. - OWASP Top 10 for LLMs · website · genai.owasp.org · free
The security checklist for LLM apps. - Papers With Code · website · paperswithcode.com · free
Papers with runnable implementations. Reading the implementation sections of seminal papers shows depth. - Perplexity · tool · perplexity.ai · free
AI research tool, also handy for explaining error messages. - Phind · tool · phind.com · free · link looked broken
Developer-focused AI search. - Prompt Engineering Guide · website · promptingguide.ai · free
A reference for prompting techniques. - Railway · tool · railway.com · free
Deploy apps and APIs quickly. - Render · tool · render.com · free
Simple app and service hosting. - Replit · tool · replit.com · free
Browser-based coding for learning Python without any setup. - smolagents · docs · huggingface.co · free
Hugging Face's minimalist agent framework. - Weights & Biases · tool · wandb.ai · free
Experiment tracking and dashboards. - Zapier · tool · zapier.com · free
Connect apps without code.
Try this
- Study LLM basics: tokens, embeddings, context windows, and model selection.
- Build a RAG app with hybrid search, reranking, and citations, and debug its retrieval failures.
- Build an agent with retries and human approval.
- Evaluate both projects on retrieval quality, answer accuracy, task success, latency, and cost.
- Open-source your projects, get users, fix what breaks, and measure what improves.
- Rewrite your resume bullets to show the problem, the tools, and the impact.
- Practice explaining your design decisions and failure handling for interviews.
- Search job boards by skill keywords (RAG, RAGAS, Agents, LLM, LangChain) and by alternative titles (Forward-Deployed Engineer, AI Solutions Engineer).
- RAG app with hybrid search, reranking, and citations, evaluated on retrieval quality and answer accuracy.
- Agent that researches companies or updates a CRM, with retries and a human approval step, evaluated on task success, latency, and cost.