Elevate AI agent evaluation as an Applied Machine Learning Scientist with Vector Institute. This role involves advanced research on improving agent performance and safety in team-oriented, hybrid environments.

In the role at Vector Institute, you will lead research focused on evaluating AI agents over long timelines and multiple tasks. Your expertise in Python and understanding of AI systems will drive adaptive evaluation frameworks critical for Canadian organizations. This position offers the chance to improve safety and reliability of AI with practical applications.

Key Responsibilities:



• Implement state-of-the-art evaluation methods • Develop techniques for organization-specific assessments • Create durable regression evaluations from discovered failures • Collaborate with researchers on evaluative tools • Lead peer-reviewed outputs and technical reports

Requirements: • PhD in computer science or related field • Experience in AI evaluations and language models • Solid statistical and experimental design skills • Familiarity with contemporary machine learning frameworks • Proven track record of effective communication

Harness your expertise and contribute to meaningful advancements in AI safety and evaluation at the Vector Institute. #J-18808-Ljbffr

📌 Machine Learning Scientist At Vector Institute Toronto
🏢 Vector Institute
📍 Toronto