About the Role
Join a small, senior team building autonomous AI agents for executive workflows. You will develop agent capabilities and evaluation systems that help ensure real-world tasks are completed reliably, with measurable improvements reaching users quickly.
What You'll Do
Build agents that complete delegated work end to end, without requiring users to check each step.
Define measurable success criteria and trusted ways to assess agent performance across tasks.
Develop and evaluate new agent capabilities before releasing them to users.
Investigate production failures and deliver durable fixes based on their underlying causes.
Build systems to detect known failure patterns and less predictable issues at scale, using tools such as Braintrust and Raindrop.
Improve agent recovery when tools or websites fail.
Create repeatable evaluation workflows that let engineers measure whether changes improve agent performance.
What We're Looking For
At least 3 years of data science or machine learning experience building evaluation systems, metrics, or product quality measurement.
Production-quality Python and SQL skills for analysis, large datasets, and automated pipelines.
Experience designing evaluation frameworks, representative datasets, meaningful metrics, and realistic end-to-end simulations.
A track record delivering production AI, ML, agent, or agent-evaluation systems for real users and measuring their impact.
Experience improving agent reliability, owning systems end to end, and using statistics and experiment design to evaluate changes.
Familiarity with post-training, fine-tuning, or reinforcement learning is useful.
Experience with Django, React, and TypeScript; the role also uses Python, SQL, Braintrust, and Raindrop.
Demonstrated progression and sustained experience in a role, with comfort working in a fast-moving, ambiguous environment.
Compensation & Benefits
Base salary: $200,000 to $300,000 annually. Visa sponsorship is not available.
Location
On-site in Palo Alto, California.