Data Scientist, Agent Evaluations & Quality

Clera is seeking a Data Scientist to own the end-to-end measurement of autonomous agent quality. You will translate ambiguous product behavior into rigorous evaluation systems that directly guide engineering and product decisions for our AI productivity startup.

• Architect and maintain automated evaluation pipelines for agent quality
• Define and track key metrics like task success, latency, and reliability
• Build representative gold datasets and regression suites
• Design grading systems and calibrate LLM-as-a-judge solutions
• Analyze traces to identify root causes and build a failure taxonomy
• Communicate evaluation results to technical and non-technical stakeholders

• No visa sponsorship is available.