Member of Technical Staff, Agents
Core
Build autonomous AI agents and evaluation systems to ensure reliable completion of delegated executive workflows.
Role type
Senior IC machine-learning engineer (agent evaluation & reliability)
Builds
Autonomous AI agents for executive workflows
Domain
AI Agents / Executive Productivity
Deliverable
production ML models
Required skills
Python, SQL, evaluation framework design, statistics, experiment design, end-to-end simulations, fine-tuning, post-training, reinforcement learning
Preferred skills
Django, React, TypeScript, Braintrust, Raindrop
Responsibilities
Build agents that complete delegated work end to end, define reliable measures of success for agent tasks, develop new agent capabilities, investigate production failures, build systems to detect failure patterns at scale, improve agent recovery when tools or websites fail, create repeatable methods to measure impact of agent changes
