About this role
AI Engineer, Evaluation at Distyl. Location: San Francisco or New York City. Role: designing evaluations, building pipelines, operating graders Requirements: 2+ years software engineering, strong Python, experience with evaluation- or experiment-driven development, ability to encode human judgment into tests/graders, systems-oriented mindset, and willingness to travel 10–50%. Category: Engineering Seniority: Entry Level Tools: Python, LLM Commitment: Full Time Workplace: Hybrid Languages: English