Cohere
Senior
Own the runtime that makes Cohere's North agents reliable at enterprise scale
Interview for Cohere's Agent Harness PM role on the North platform, owning the agent loop, context engineering, and the feedback bridge between engineering and the Modeling team. Expect deep technical questioning on agent architecture, evals, and implementation-level tradeoffs, not just roadmap storytelling.
走进这场面试
免费 · 一场按这个岗位校准的真语音模拟
这场面试考什么
- Agent loop and execution runtime design (tool orchestration, parallel execution, sub-agent delegation, sandbox execution, failure recovery)
- Context engineering as a controlled resource (progressive disclosure, compaction/summarization, filesystem offloading)
- Agentic evaluation framework design bridging product and research
- Diagnosing model gaps vs. scaffolding gaps
- Cross-functional partnership with an ML Modeling/research team
- Enterprise agentic deployment constraints (multi-tenant orchestration, tool permissioning, audit trails, air-gapped environments)
常见提问方向
Walk me through a time you contributed to an architecture decision at the implementation level rather than just writing requirements
How would you design an eval framework that both the harness team and the Modeling team trust as their shared source of truth?
A North agent fails on a long, multi-step enterprise task — how do you determine whether it's a model limitation or a harness/scaffolding limitation?
How do you think about managing an LLM's context window as a deliberately controlled resource across a long agent trajectory?
How would you validate a new harness capability (e.g., sub-agent delegation) with a research/Modeling team before committing engineering to build it?
Tell me about engaging an enterprise customer to surface a real agentic failure and translating it into a concrete product requirement
相关面试
Cohere
Mid
Forward Deployed Engineer, Agentic Platform
Cohere
Mid
Member of Technical Staff, Applied ML
Cohere
Senior
Data Engineer, Data Foundations
Ramp
Mid
Product Manager | Agentic CX
Senior
Senior Software Engineer, Enterprise AI
Databricks
Senior