Elevate AI systems with Vector as an Applied Machine Learning Scientist. Focus on agent evaluation, observability, and stress-testing across long-horizon tasks for Canadian organizations. This role entails leading innovative research aimed at enhancing AI agent performance and safety. Working collaboratively with Vector researchers and external partners, you'll develop tailored evaluation methods that move beyond static benchmarks.

Key responsibilities include assessing agent trajectories, developing organization-specific evaluations, and creating reliable systems to measure and improve agent effectiveness. Key Responsibilities:

- Research evaluation methods for long-horizon agents
- Develop comprehensive assessments of agent performance
- Create organization-specific evaluations from production data
- Construct durable regression tests for agent failures
- Collaborate with researchers and industry partners Requirements:
- PhD in computer science or related field
- Expertise in AI agent evaluation and safety
- Proficiency in Python and research software
- Experience with up-to-date language models
- Strong analytical skills in experimental design Become a pivotal resource in enhancing safe AI agents at Vector Institute.

📌 Lead Machine Learning Scientist at Vector (Toronto)
🏢 Vector Institute
📍 Toronto