Remote LLM Red Team Specialist - Frontier Model Vetting

Obsidian; New York (NY); On-site; USD 110,000 - 170,000; Full time

Job summary

Cincinnatus LLC is building capabilities to stress-test frontier AI models. You will work in a red-teaming setup to design and probe multi-step tasks that reveal vulnerabilities, edge cases, and failure modes in cutting-edge AI systems, with approximately 35 hours per week and fully remote work within the United States.

This is a full-time W-2 role, where you collaborate with researchers to turn findings into stronger benchmark tasks, document evidence and reproducible steps, and help the

Qualifications

• MSc or PhD in a STEM field, or equivalent practical experience in a research-heavy domain requiring data analysis and coding.
• 1+ years of experience 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 your own 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: high attention to detail, creativity in finding what others missed, strong written communication, and the ability to work independently through ambiguous, open-ended problems.
• Ability to engage reliably for approximately 35 hours per week.

Responsibilities

• Probe models: Explore frontier AI models on coding, ML, and analysis tasks, finding spots where they quietly err.
• Design challenges: Turn weaknesses into well-crafted tasks that are hard for models but fair to grade.
• Document findings: Write up evidence and steps that others can reproduce.
• Strengthen tasks: Collaborate with authors to close loopholes, shortcuts, and grading gaps.
• Work as a team: Share insights with researchers and experts to improve benchmarks.

Skills

Python

Git

LLM evaluation

Red-teaming

Research proficiency

Education

MSc or PhD in STEM

Tools

Python tooling

Job description

Cincinnatus LLC is building capabilities to stress-test frontier AI models. You will work in a red-teaming setup to design and probe multi-step tasks that reveal vulnerabilities, edge cases, and failure modes in cutting-edge AI systems, with approximately 35 hours per week and fully remote work within the United States.

This is a full-time W-2 role, where you collaborate with researchers to turn findings into stronger benchmark tasks, document evidence and reproducible steps, and help the