5 hours ago
Palo Alto, CA, USASenior
Base Salary
$200k - $300k/yr
Responsibilities
- Build autonomous agents that complete delegated executive workflows end to end.
- Develop reliable measures of agent task correctness and system reliability.
- Design new agent capabilities and validate them before launch.
- Investigate production failures and implement fixes for underlying system issues.
- Build scalable detection for known failures and emerging patterns.
- Improve agent recovery when tools or websites fail.
- Make agent changes measurable and repeatable for engineering assessment.
Requirements
- Experience building or improving production AI agents or other applied machine-learning systems.
- Background in evaluation, harness engineering, or measuring AI-system reliability.
- Strong Python skills and familiarity with Django, React, and TypeScript.
- Ability to investigate ambiguous problems across system components and connect technical improvements to user outcomes.
- Familiarity with AI evaluation tools such as Braintrust or Raindrop is relevant.
Benefits
- Salary range of $200,000 to $300,000 USD annually.
- On-site role in Palo Alto, California, with four days per week in the office.