Small, mission-driven team using AI to make critical systems safer is looking to grow their Data Science team. Focusing on building tools and models that improve safety, security, and trust in AI systems, including benchmarking LLMs, evaluating risks, and automating nuanced workflows.

We’re looking for a Data Scientist to help shape how they measure, analyze, and optimize their products.

You will:

• Build internal and external metrics systems to track product performance.
• Develop BI dashboards to provide actionable insights.
• Run post-data analyses to inform product decisions in collaboration with the team.
• Benchmark our system against different LLMs and evaluate performance.
• Design and analyze A/B tests to improve product features.

Requirements:

• Strong experience in Python and SQL for data analysis and workflow automation.
• Proven ability to build internal and external metrics systems.
• Experience developing BI dashboards and running post-data analyses to guide product decisions.
• Familiarity with A/B testing design and analysis.
• Experience benchmarking ML systems, ideally LLMs, and evaluating their performance.
• Ability to work cross-functionally with product, engineering, and research teams.

‍

Nice-to-Have:

• Experience with trust & safety, moderation, or security-focused ML
• An advanced degree in computer science or a related field.

‍