GenAI Red Team Engineer — Remote, 35h/wk

Mercor; San Francisco (CA); On-site; USD 100,000 - 140,000; Full time

Job summary

Mercor is hiring for a full-time remote role within the United States to probe frontier AI models, find weaknesses, and design robust evaluation tasks. You'll work with researchers to produce reproducible findings and strengthen benchmarks in a collaborative team.

The role requires 1+ years in an AI evaluation or related research field and advanced credentials (MSc/PhD in a STEM field). Strong Python and Git skills, plus knowledge of LLM capabilities, are essential.

Qualifications

• MSc or PhD in a STEM field or equivalent research experience.
• 1+ year in a research, research-engineering, security, or AI-evaluation role.
• Proven ability to identify vulnerabilities, edge cases, or failure modes in LLMs/ML systems.

Responsibilities

• Probe frontier AI models to identify weaknesses in coding, ML, and analysis tasks.
• Design challenging, fair-to-grade tasks that expose model gaps.
• Document findings with clear evidence and reproducible steps.

Skills

Python

Git

LLM evaluation

Adversarial testing

Data analysis

Written communication

Education

MSc or PhD in STEM

Job description

Mercor is hiring for a full-time remote role within the United States to probe frontier AI models, find weaknesses, and design robust evaluation tasks. You'll work with researchers to produce reproducible findings and strengthen benchmarks in a collaborative team.

The role requires 1+ years in an AI evaluation or related research field and advanced credentials (MSc/PhD in a STEM field). Strong Python and Git skills, plus knowledge of LLM capabilities, are essential.