Particle Physics AI Benchmark Architect

Mercor; New York (NY); On-site; USD 83,000 - 165,000; Full time

Job summary

Mercor is seeking a Particle & Nuclear Physics Expert to design graduate-level computational problems for AI benchmarking. You will craft scenarios requiring real scientific software usage, running simulations, interpreting results, and designing experiments to reveal hidden information from data.

We value hands-on experience with scikit-hep and related HEP Python tools, plus strong Python skills to implement problem setups, validators, and tools for reproducibility in a Linux/terminal

Qualifications

• Graduate-level training in a STEM field (MS/PhD preferred).
• Proven proficiency with at least one scientific software library or toolkit.
• Strong Python skills for writing problem setups and validators.
• Ability to work independently and refine designs from feedback.
• Comfortable in a Linux/terminal environment with remote compute sandboxes.
• Available for at least 15–20 hours per week.

Responsibilities

• Design original graduate-level problems using real scientific workflows.
• Use specialized software to run simulations and interpret results.
• Create multi-step experiments and strategic queries for AI models.
• Test problems against state-of-the-art models and refine difficulty.
• Collaborate with peers to ensure problem quality and reproducibility.

Skills

Python

scikit-hep

Education

MS or PhD in Physics or related STEM field

Tools

Linux/Unix

Scientific software libraries

Job description

Mercor is seeking a Particle & Nuclear Physics Expert to design graduate-level computational problems for AI benchmarking. You will craft scenarios requiring real scientific software usage, running simulations, interpreting results, and designing experiments to reveal hidden information from data.

We value hands-on experience with scikit-hep and related HEP Python tools, plus strong Python skills to implement problem setups, validators, and tools for reproducibility in a Linux/terminal