Product Manager

About the role

Join our team as a Product Manager for the Agent Harness. In this role, you will own the execution layer that makes North agents reliable, capable, and production-ready. You will engage at the implementation level, contribute to architecture decisions, and define the roadmap for North's agent harness. You will also serve as the primary interface between North engineering and Cohere's Modeling team, own North's agentic evaluation framework, engage with enterprise customers, and stay current with the open-source and commercial agent ecosystem. Key missions: Définir et posséder la feuille de route pour le harnais d'agent de North, y compris la boucle d'agent, la couche d'ingénierie contextuelle, l'orchestration des outils, l'exécution en bac à sable et la délégation de sous-agents.. Servir d'interface principale entre l'ingénierie de North et l'équipe de modélisation de Cohere, en veillant à ce que les nouvelles capacités du harnais soient validées avant d'être construites.. Posséder le cadre d'évaluation agentique de North, en veillant à ce que les évaluations soient compatibles à la fois avec le harnais de North et l'infrastructure de formation de la modélisation. Profile: - Technically deep enough to contribute to architecture decisions at the implementation level: comfortable reviewing and shaping design docs, reasoning about async execution patterns, sandboxed environments, filesystem design, and the tradeoffs that come with building harness capabilities into a production platform - Strong grasp of agentic evaluation design, including how to measure task completion, failure recovery, and long-horizon reliability, and how to diagnose model vs. scaffolding gaps - 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 - Track record of shipping platform-layer products with demonstrated impact on reliability, performance, or capability - Ability to flex between ML research conversations and engineering architecture discussions with equal fluency - An active practitioner of agent frameworks who regularly builds with and follows the latest developments in open-source harnesses, coding agents, and orchestration tools in both professional and personal work - Hands-on experience with enterprise agentic deployments: multi-tenant orchestration, tool permissioning, audit trails, and compliance requirements - Familiarity with infrastructure constraints relevant to enterprise deployments: on-premises environments, scalability challenges, and the operational tradeoffs of running complex agent workloads in restricted or air-gapped settings - Prior work at the intersection of research and product, translating nascent model capabilities into shipped product features - Background working within or closely alongside an ML research or post-training team - If some of the above doesn’t line up perfectly with your experience, we still encourage you to apply!