Product Manager, Agent Harness & Modelling
SKILLS
FULL DESCRIPTION
Product Manager, Agent Harness & Modelling
[Employer hidden — sign up to reveal] is hiring a Product Manager for its Agent Harness & Modelling team to own the execution layer of North, an enterprise agentic AI platform. The role involves defining the roadmap for agent harness, context engineering, tool orchestration, and evaluation frameworks, while bridging product engineering with the Modelling team. Requires 5+ years of PM experience in AI systems and deep technical expertise in LLM agent architectures.
Role Overview
We are seeking an Agent Harness Product Manager to own the execution layer that makes North agents reliable, capable, and production-ready. This is a role that sits at the intersection of three domains:
- Agent Loop and Execution: Own the core agent runtime: tool orchestration, parallel execution, sub-agent delegation, sandbox code execution, and failure recovery.
- Context Engineering: Own how our Agents manage the context window as a deliberately controlled resource.
- Model-Scaffolding Co-evolution: Own the feedback loop between North's harness and the Modeling Team.
Responsibilities
- Define and own the roadmap for North's agent harness, including the agent loop, context engineering layer, tool orchestration, sandbox execution, and sub-agent delegation.
- Serve as the primary interface between North engineering and [Employer hidden — sign up to reveal]'s Modeling team, ensuring new harness capabilities are validated before being built.
- Own North's agentic evaluation framework, ensuring evals are compatible with both the North harness and Modeling's training infrastructure.
- Engage enterprise customers to surface real-world agentic failures and translate findings into concrete product and model requirements.
- Stay current with the open-source and commercial agent ecosystem and drive adoption decisions.
Requirements
- 5+ years of product management experience in agentic AI systems, developer infrastructure, or applied ML products.
- Deep understanding of modern LLM agent architectures, including multi-agent systems, tool-augmented reasoning, memory and retrieval, programmatic orchestration, RAG, and long-horizon execution.
- Strong grasp of agentic evaluation design, including how to measure task completion, failure recovery, and long-horizon reliability.
- Technically deep enough to contribute to architecture decisions at the implementation level.
- Ability to flex between ML research conversations and engineering architecture discussions.
- Track record of shipping platform-layer products with demonstrated impact.
Why Join [Employer hidden — sign up to reveal]?
- Impact: Shape how Canada's most important public institutions adopt and deploy frontier AI.
- Innovation: Work alongside leading researchers and engineers solving complex ML challenges.
- Growth: Competitive compensation, equity options, and opportunities for professional development.
- Flexibility: Hybrid work model with offices in key global locations (Toronto, Montreal, New York, San Francisco, London, Paris, and Korea).
[Employer hidden — sign up to reveal] values and celebrates diversity. If some of the above doesn’t line up perfectly with your experience, we still encourage you to apply!
Full-Time Employees at [Employer hidden — sign up to reveal] enjoy these Perks: open culture, work with cutting-edge AI team, weekly lunch stipend, full health and dental, 100% Parental Leave top-up, personal enrichment benefits, remote-flexible, 6 weeks of vacation.