Cohere
Senior
Build the secure-execution and identity infrastructure that runs Cohere's autonomous AI agents
Cohere's Agentic Platform team is building next-generation infrastructure for autonomous AI agents: secure code execution, agent state management, model routing, identity/authentication, and resource management for long-running workflows. This interview targets engineers with production ML infrastructure and distributed systems depth who can turn emerging, pattern-less research ideas into reliable platform capabilities.
Step into this interview
Free · a live voice mock calibrated to this exact role
What this interview tests
- Secure execution/sandboxing for untrusted (agent-generated) code
- Identity, authentication, and trust boundaries for non-human callers
- Model routing and orchestration across model providers/environments
- Rate limiting, quotas, and resource management at scale
- State/memory/filesystem abstractions for long-running agents
- Judgment in productionizing research prototypes with few established patterns
Common question themes
Design a sandbox for executing untrusted, agent-generated code safely
How would you design identity and permission scoping for an autonomous agent
Design a rate-limiting/quota system for many concurrent long-running agent workflows
Tradeoffs in routing requests across different LLM providers/model types
Tell me about taking a research idea to production infrastructure with no existing playbook
Related interviews
Cohere
Mid
Forward Deployed Engineer, Agentic Platform
Cohere
Mid
Member of Technical Staff, Applied ML
Cohere
Senior
Data Engineer, Data Foundations
Affirm
Senior
Senior Software Engineer, Backend (Merchant Data Platform EU)
Cloudflare
Mid
Threat Intelligence Software Engineer, Cloudforce One
Figma
Senior