Loading...

AI Red Teamer

10a Labs

About 10a Labs: 10a Labs is the safety and threat-intelligence layer trusted by frontier AI labs, AI unicorns, Fortune 10 companies, and leading global technology platforms. Our adversarial red teaming, model evaluations, and intelligence collection enable engineering, safety, and security teams to stay ahead of evolving threats and deploy AI systems safely.

In This Role, You Will

  • Develop and run adversarial test suites—both manual and scripted—for LLMs and image / video models.
  • Craft multilingual prompts, jailbreaks, and escalation chains targeting policy edge cases.
    Analyze outputs, triage failures, and write concise vulnerability reports.
  • Contribute to internal tooling (e.g., prompt libraries, scenario generators, dashboards).

We’re Looking for Someone Who

  • Has 2-4 years of experience in red-teaming, security research, trust & safety, or related fields.
  • Is comfortable scripting basic tests (Python, Bash, or similar) and working in Jupyter or prompt-engineering tools.
  • Communicates clearly in English and at least one additional language (ideally major non-English language relevant to global threat landscapes).
  • Thinks like an adversary, documents findings crisply, and iterates quickly.

Requirements

  • Bachelor’s degree—or equivalent experience—in CS, data science, linguistics, international studies, or security.
  • Basic proficiency with Python and command-line tools.
  • Demonstrated interest in AI safety, adversarial ML, or abuse detection.
  • Strong writing skills for short vulnerability reports and long-form analyses.
  • Ability to rapidly context switch across domains, modalities, and abuse areas.
  • Excited to work in a fast-paced and ambiguous space.

Nice to Have

  • Full professional proficiency in Arabic, Chinese, Farsi, Portuguese, Russian, or Spanish, as well as English.
  • Prior work in content moderation, disinformation analysis, or cyber-threat intelligence.
  • Experience with prompt-automation frameworks (e.g., Promptfoo, LangChain, Garak).
    Familiarity with vector search or LLM fine-tuning workflows.
  • Formal training or certification in red-teaming or penetration testing.

Compensation & Benefits

  • Salary range: $70K–$90K depending on experience.
  • Opportunity for spot bonuses and annual performance-based bonus.
  • Fully remote (U.S.-based) with flexible hours.
  • Comprehensive health, dental, and vision.
  • Generous PTO and paid holidays.
  • 401(k) plan.
  • Professional-development stipend for courses, conferences, or language study.
  • We reward excellence with growth—team members who excel have clear paths for promotion and skill development.

To apply for this job please visit job-boards.greenhouse.io.

Terms used in this posting

PTO
Paid Time Off — vacation, personal, or sick days you can take while still being paid.

Working in Washington, D.C., US

Weather right now in Washington, D.C., US: checking… · Local time: · Air quality: · Daylight: · UV index:

Washington, D.C., officially the District of Columbia and commonly known as Washington or D.C., is the capital city and federal district of the United States. The city is on the Potomac River across from Virginia and shares land borders with Maryland to its north and east. It was named after George Washington, a Founding Father and the first president of the United States. The district is named fo

🇺🇸 Relocation safety for US: Exercise Normal Cautionvia Warnely, CC BY 4.0

National unemployment rate in US: 4.2%via World Bank

  • Elevation 7m (23 ft)

Source: Wikipedia (state)

Job details above are provided by the employer/source. The sections on this page are compiled from public data sources with AI assistance.

Accommodations: if you need a workplace accommodation to apply for or perform this job, see ADA.gov or EEOC.gov for guidance on your rights and how to request one.

Add application deadline to calendar

Keep exploring on Get A Job.ai

Not quite the right fit? Your next opportunity is a click away.

Hiring instead? Post a job and reach candidates searching right now.