ML engineer, graders
Design graders that agree with people and prove it.
You will build and measure the graders customers rely on: correctness, policy, tone and faithfulness.
You have shipped an LLM feature and measured it with labeled data, not vibes.
Team
Research
Location
Remote, US time zones
Type
Full time
Salary
$180,000 to $210,000
Send a resume or a link, plus two sentences on something you built. A person replies within a week.