and scoring logic to evaluate agent actions Analyze agent logs, failure modes, and decision paths Work with code repositories... limits) and how these affect evaluation design Familiarity with Docker English proficiency - B2 How it works...
AI Engineer, you will join our Data team (60+ people) to prototype, iterate, and integrate agentic systems into Mirakl products... for a Permanent contract (CDI) or Freelance, based in Paris, Bordeaux, or Full Remote from France. Our stack and tools: Python...