Research
Applied AI Researcher, Evals
Develop methods to measure agent decisions and actions, and turn production runs into reliable test suites.
San Francisco · Hybrid
Full-time
$210k – $260k + equity
About the role
Develop methods to measure agent decisions and actions, and turn production runs into reliable test suites. You’ll join a small team that ships every week and talks to customers directly.
What you’ll do
Develop evaluation methods for agent decisions and actions
Build datasets from production runs with strict privacy controls
Write up findings for customers and the wider community
Work with engineering to ship evals into the product
What you’ll bring
Experience evaluating ML systems in production
Strong statistics and experiment design
Python, and a bias for shipping
Benefits
Competitive salary and meaningful equity
Private health, dental and vision cover
16 weeks of fully paid parental leave
$2,000 yearly learning budget
Two company offsites a year
APPLY FOR THIS ROLE
Applied AI Researcher, Evals