GenAI Vulnerability Engineer (Remote, 35h/wk)

Mercor; New York (NY); Remote; USD 120,000 - 170,000; Full time

Job summary

Mercor is seeking specialists to join a leading AI lab's GenAI team as part of an extended workforce placed at a top AI lab in a fully remote role within the United States. You will work on red-teaming frontier AI systems, designing complex multi-step tasks and documenting findings to expose vulnerabilities and improve benchmarks.

The role emphasizes independent work with 35 hours weekly, collaboration with researchers, and iterative task improvement.

Qualifications

• MSc or PhD in a STEM field, or equivalent practical research experience.
• 1+ years in a research, research-engineering, security, or AI-evaluation role.
• Demonstrated ability to identify vulnerabilities, edge cases, or failure modes in LLMs or ML systems.
• Working proficiency in Python and Git, with the ability to script probes and analyses.
• Strong familiarity with LLM capabilities, limitations, and evaluation techniques.
• Past experience in AI training, model evaluation, or benchmark/task authoring is preferred.
• A perfectionist mindset with high attention to detail and strong written communication.
• Ability to engage reliably for approximately 35 hours per week.

Responsibilities

• Probe frontier AI models to identify how they behave on coding, ML, and analysis tasks.
• Design challenging tasks that are hard for models but fair to grade.
• Document findings with evidence and reproducible steps.
• Strengthen tasks by closing loopholes, shortcuts, and grading gaps.
• Collaborate with researchers to improve benchmark quality.

Skills

Python

Git

Data analysis

Research experience

Adversarial testing

Education

MSc or PhD in STEM

Equivalent practical research experience

Tools

Jupyter

Job description

Mercor is seeking specialists to join a leading AI lab's GenAI team as part of an extended workforce placed at a top AI lab in a fully remote role within the United States. You will work on red-teaming frontier AI systems, designing complex multi-step tasks and documenting findings to expose vulnerabilities and improve benchmarks.

The role emphasizes independent work with 35 hours weekly, collaboration with researchers, and iterative task improvement.