For companies:
For professionals:
For everyone:
For developers:
Responsibilities
How do you test something that gives a different answer every time you ask it?That's the puzzle for our next AI Quality Analyst.You’ll build automated evaluation pipelines (LangSmith, DeepEval, etc.), track quality across agent workflows, run hallucination analysis, and wire eval gates into CI/CD.Python + Real intuition for LLM behavior required.If you have never heard of AI harnesses, only have a manual-coding mindset, are more ML than entrepreneurial, and don’t ask weird questions like “how do you grade a judge that’s grading another judge that grades another AI agent?” then this position is probably not for you.
This job post is closed.