Product Data Scientist — AI Evaluation & Quality

What You Will Be Doing:

• Own and extend our offline eval suite across products — datasets, judges, metrics.
• Build and maintain online quality dashboards: resolution rate, CSAT, LLM-as-judge signals.
• Close the production feedback loop: mine failure patterns, turn into regression cases, propose fixes.

Must-Haves:

• Python and SQL — build an analysis end-to-end.
• Solid foundation in statistics — sampling, hypothesis testing, variance.
• Analytical mindset — start from the business question, not from the tool.

Nice-to-Haves:

• Experience in quality analytics for ML systems.
• Hands-on experience evaluating LLM applications (RAG, agents, tool use).
• Experience building LLM agents — side projects count.

What You Will Get In Return:

• Make a genuine impact on the product.
• Work in the EU with remote flexibility.
• Become a stock options holder and align your aspirations with ours.