Remote Python AI Evaluation Engineer

Build Python pipelines for AI evaluation at Turing while shaping preference data and rubric quality in a fully remote environment. Clear technical writing and judgment matter here.

Turing seeks an engineer experienced with preference data, rubric creation, and high-quality evaluation work. You will support frontier AI labs by turning qualitative judgment into scalable processes. The work combines engineering, data review, communication, and collaboration with researchers and engineers.

• Design and refine rubrics for preference data evaluation
• Review and label data while catching subtle quality issues
• Build pipelines supporting data generation and evaluation workflows
• Synthesize findings into clear updates and recommendations
• Translate qualitative judgment into scalable team processes

• Proficiency in Python for pipelines and infrastructure
• Hands-on preference data or rubric creation experience
• Strong written and verbal communication skills
• Ability to explain why examples demonstrate quality
• Minimum six-hour overlap with Pacific Time preferred

Apply Python engineering, preference data expertise, and high-taste judgment to Turing’s remote AI evaluation work.