Member of Technical Staff, Agents
Core
Build autonomous agents that complete delegated work end to end, develop evaluations for agent accuracy, and ship agent capabilities in existing user tools.
Role type
Senior IC machine-learning engineer (agents/LLM)
Builds
Autonomous agents and agent capabilities integrated into user tools
Domain
AI / Machine Learning / LLM-powered products
Deliverable
production ML models
Required skills
Python, Django, React, TypeScript, agent development, LLM evaluation, failure detection, workflow creation
Preferred skills
Experience with evaluation tools (Braintrust, Raindrop), production AI/ML system experience
Technologies
Python, Django, React, TypeScript, Braintrust, Raindrop
Responsibilities
Build autonomous agents that complete delegated work end to end; Develop evaluations that measure agent accuracy across different tasks; Ship agent capabilities in existing user tools with evidence of readiness; Investigate production failures and deliver durable, validated fixes; Build large-scale failure detection for known and unexpected issues; Create repeatable workflows for measuring whether agent changes improve performance
Seniority
Mid-to-Senior, hands-on IC
