Senior Software Engineer - AI Data
Remote · from United States
Core
Evaluate AI coding agents' work by running their output on real engineering tickets and identifying model mistakes in a familiar codebase.
Role type
Senior IC software engineer (AI evaluation)
Builds
Production ML models (coding agents)
Domain
AI / Software Engineering
Deliverable
production ML models
Required skills
Software engineering, coding, code review, debugging, problem solving
Preferred skills
AI model evaluation, prompt engineering
Technologies
AI Support
Responsibilities
Give coding agents real tickets, run their output, and evaluate their work as you would a teammate's pull request; Work through real engineering problems in a familiar codebase alongside an AI agent, step by step, and identify where the model makes mistakes
Seniority
Senior, hands-on IC