Research Engineer

Job Summary

To support the development of cutting-edge AI models, the full-time Research Engineer will design evaluations and build environments for training, working remotely or in-person in San Francisco.

Key responsibilities

• Design and build challenging evaluations for coding and long-horizon agents
• Develop and test scoring logic and verifiers, investigating reward hacks and misleading measures of progress
• Build and scale RL data pipelines that generate and curate challenging coding and agentic tasks

Required qualifications

• Strong software engineering skills in Python with experience in data pipelines or ML workflows
• Hands-on experience with language models or agents, understanding their training data and evaluation impacts
• Proven ability to inspect complex data and model outputs to identify failure modes
• Experience owning technical projects through experimentation and collaboration with researchers
• Hands-on experience building technical evaluations or agent environments