Teaching AI Engineering Concepts

I run a community where experienced software engineers become AI engineers by building real, production-grade LLM projects I'm looking for an AI engineer who can teach hands-on concepts and project videos related to AI Engineering, as an ongoing part of the team. New projects and topics are added regularly, so there's steady work for the right person. You'll be recording hands-on video lessons (screen recording) that walk through building real LLM projects step by step, explaining the why, the tradeoffs and the failure cases etc. Topics you'll teach (current and upcoming) - LLM fundamentals: prompting, structured output, streaming, tool use - RAG: chunking, embeddings, vector databases, retrieval, citations, reranking - Agents: LangGraph and similar, tool calling, text-to-SQL, multi-step workflows - Evaluation and observability: golden sets, LLM-as-judge, tracing (Langfuse or similar) - Production: guardrails, prompt injection, cost and latency, caching, deployment, CI/CD - Working with AI coding tools in a real codebase - New topics as the field moves (fine-tuning, multimodal, voice agents, and so on) Requirements: - 3+ years writing production Python - Shipped at least one LLM app beyond a demo: RAG, agents or text-to-SQL, ideally with evals - Hands-on with the modern LLM stack (LangChain/LangGraph, a vector database, FastAPI or similar) - Clear spoken English, and a decent mic - A habit of explaining why, not just what: tradeoffs, failure cases, how you debugged it - You keep up with new models and tools, and enjoy teaching I'll pick 3–4 applicants for a short, stand-alone paid trial