Director, Evaluations

Highlights

• Build and lead LawZero's independent Evaluations Team for Scientist AI.
• Define world-class evaluation strategy for capabilities, safety and robustness.
• Own public model cards, reports and red-teaming programs at scale.

What they offer

• Minimum 20 days vacation per year
• Minimum 4% employer retirement savings contribution
• Generous flexible benefits to support well-being

Ideal candidate

A seasoned ML leader passionate about AI safety who thrives in ambiguity and builds rigorous, independent teams. You care about trustworthy measurement, clear communication, and advancing safe-by-design AI as a public good.

Requirements

• Advanced degree (MSc or higher) in machine learning, computer science, or closely related field
• 10+ years experience in machine learning with at least 5 years leading technical teams
• Hands-on expertise designing and running large-scale LLM evaluations for capabilities, safety and robustness
• Track record building evaluation datasets, benchmarks, or interactive environments from scratch
• Strong written and verbal communication skills for technical and non-technical audiences
• Comfortable operating in a research-driven, fast-moving environment with significant ambiguity