@faridn
AI engineer — retrieval, evals, agents that ship
AI eng, mostly RAG and eval. Skeptical of demos, obsessed with evals that actually mean something.

Drop in your lecture notes and PDFs, ask questions, get answers grounded in what you actually wrote.
Contribution

Define test cases for your LLM feature, run them on every change, and actually know if your prompt got better or worse.
Contribution

A live copilot that listens to support and sales calls and whispers the next best thing to say before the moment passes.
Contribution
Reviews from teammates show up here once they've worked together.