Senior Domain Expert, AI Model Evaluation (Seven Specialist Tracks)

Senior specialists can use their field expertise to judge how advanced AI models handle difficult, expert-level problems. The role suits experienced practitioners who still work hands-on in their discipline and can explain technical judgment clearly in writing. The work supports an AI research effort focused on model reasoning, so it is evaluation rather than production engineering.

What you'll do

• Create true-to-life problems and scenario sets in your specialty
• Write expert reference answers and the rubrics used to grade them
• Review AI-generated responses for accuracy, depth and sound domain judgment

What you'll need

• Senior experience in one of seven tracks: software/systems engineering, computational science or formal methods, GPU kernels and ML inference, security, hardware design, creative technology, or enterprise operations
• Track-specific experience of roughly 6 to 12+ years, with education from a Bachelor's up to a PhD depending on the track
• Current or recent hands-on work in your field
• Clear technical writing and comfort working on your own
• Pluses: publications or open-source work, peer or code review experience, and tools such as vLLM, SGLang, Lean, Coq or RTL/HDL

Good to know

• Contract engagement, remote
• Asynchronous, flexible schedule that can sit alongside an existing job
• Pay: $135 per hour
• Applicants go through background checks