Physics PhD, Quantum Computing Expert
Core
Develop grading criteria, create scientific prompts, and test/calibrate tasks against advanced AI models to improve model performance.
Role type
research-level AI model evaluation specialist
Builds
AI model performance improvements
Domain
Artificial Intelligence / Quantum Computing
Deliverable
research
Required skills
Python, R, scientific computing, Git/GitHub, Docker, peer-reviewed publication experience
Preferred skills
experience in scientific software or research engineering
Technologies
AI, Docker, Git, GitHub, Python, R
Responsibilities
Find source material in published papers, datasets, or repositories; Create scientific prompts based on sourced material; Develop grading criteria that define correct answers; Test and calibrate tasks against advanced models; Release tasks only when strong models fail more often than they succeed; Work independently and asynchronously to meet deadlines.
