Nuclear Nonproliferation AI Safety Analyst

Mercor; New York (NY); On-site; USD 90,000 - 120,000; Full time

Benefits offered by this job

Restaurant

Job summary

Mercor is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models, testing whether models can judge misuse potential while answering legitimate questions. You will write prompts across benign, dual-use, and adversarial levels and evaluate model responses against a defined policy standard.

The role emphasizes writing intensive work with clear rationales for non-specialists, seeking candidates with documented experience in export controls or related fields and

Qualifications

• Background in export control, treaty implementation, or programme analysis.
• Strong technical writing ability and clear rationale for non-specialists.
• Experience crafting prompts at the edge of policy and technical risk.

Responsibilities

• Write challenging single-turn prompts across benign, dual-use, and adversarial levels.
• Evaluate model responses against policy standards and judge handling quality.
• Draft reference answers and technical rationale for correct handling.

Skills

Proliferation experience

Technical writing

Prompt engineering

Job description

Mercor is assembling a panel of nuclear materials and safeguards experts to red-team frontier AI models, testing whether models can judge misuse potential while answering legitimate questions. You will write prompts across benign, dual-use, and adversarial levels and evaluate model responses against a defined policy standard.

The role emphasizes writing intensive work with clear rationales for non-specialists, seeking candidates with documented experience in export controls or related fields and