Lead LawZero's evaluation efforts as Director of AI Evaluations, ensuring trustworthy assessments of advanced AI systems. Shape the future of AI safety and integrity.
As a key hire, you will design the evaluation framework at LawZero, fostering independent assessments that meet the highest credibility standards. You will guide a team in developing benchmarks for the Scientist AI, emphasizing safety and capability measurement. Collaborate closely with research and product teams to ensure accurate evaluations that enhance public trust.
Key Responsibilities: • Define and implement evaluation strategies for AI systems • Build a team of experts in machine learning evaluation • Design benchmarks to apply consistently across AI models • Oversee the development of datasets and evaluation tools • Publicly communicate evaluation findings for transparency
Requirements: • MSc or higher in machine learning, computer science<...