Nuclear Medicine Physicist — AI Safety Prompt Engineer

Neon; United States; Remote; USD 85,000 - 115,000; Full time

Job summary

Mercor is assembling a panel of radiological safety experts to red-team frontier AI models, testing whether a model can judge misuse potential of technical requests while answering legitimate questions. You will write prompts labeled benign, dual-use, and adversarial and judge model responses against a policy standard.

This role demands written rationales accessible to non-specialists, with a focus on real custody responsibilities for medical isotopes and shielding calculations.

Qualifications

• Background in nuclear medicine or radiopharmacy with red-teaming experience is preferred.
• Ability to craft and evaluate secure prompts at specialist risk thresholds.
• Strong written justification and communication for non-experts.

Responsibilities

• Write challenging prompts across benign, dual-use, and adversarial levels.
• Evaluate model responses against a policy standard.
• Draft reference answers with technical reasoning and safe-use guidance.

Skills

Nuclear medicine

Radiopharmacy

Medical physics

Radiochemistry

Tools

GMP/QA

Job description

Mercor is assembling a panel of radiological safety experts to red-team frontier AI models, testing whether a model can judge misuse potential of technical requests while answering legitimate questions. You will write prompts labeled benign, dual-use, and adversarial and judge model responses against a policy standard.

This role demands written rationales accessible to non-specialists, with a focus on real custody responsibilities for medical isotopes and shielding calculations.