AI Safety & Alignment
Director, Evaluations
Montreal, Canada
-
In this role, you'll build and lead LawZero's Evaluations Team, defining strategy for independent assessment of AI capability and safety claims.
-
Scale the team to approximately 8-10 people across research, engineering, dataset design, and red-teaming roles.
-
Design benchmarks, datasets, and environments to measure AI performance across capabilities, safety, and adversarial robustness.