AI Engineer / AI Software Engineer-Task Creator (RL Environments) (Contract)
Core
Designing realistic multi-step scenarios on Linux desktops to test AI agents' ability to perform real-world tasks using files and applications.
Role type
Contract AI Engineer (RL Environment & Task Creator)
Builds
Hard, realistic evaluation tasks for AI agents
Domain
AI evaluation, Reinforcement Learning, Computer Use Agents
Deliverable
production ML models | product features
Required skills
Python, Linux/Ubuntu terminal usage, Git, AI/ML project experience, AI coding tools proficiency
Preferred skills
Building RL environments, creating benchmarks for computer-use agents, familiarity with OSWorld
Responsibilities
Design multi-step scenarios across applications, create necessary files (spreadsheets, documents, emails), write AI agent instructions, write Python for environment setup and automated scoring, test and document tasks
Seniority
Individual Contributor, Task-based Contract
