Full-Time

AI Red Teamer Entry Level

Posted on 7/10/2025

10a Labs

10a Labs

51-200 employees

AI security research and threat intelligence

Compensation Overview

$60k - $70k/yr

+ Spot Bonus + Annual Bonus

Washington, DC, USA

Remote

Category
IT & Security (1)
Required Skills
LLM
Python
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.
Responsibilities
  • 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).
Desired Qualifications
  • 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.

10a Labs provides intelligence and research services to help technology companies secure their artificial intelligence systems. The company works by stress-testing AI models through red teaming, monitoring the dark web for jailbreak techniques, and using a proprietary classification system to moderate content in real-time. Unlike standard cybersecurity firms, 10a Labs focuses specifically on AI-related risks, including physical infrastructure challenges like data center security and supply chain vulnerabilities. Their goal is to provide leaders with the data and guidance needed to anticipate emerging threats and ensure their AI innovations remain safe and compliant.

Company Size

51-200

Company Stage

N/A

Total Funding

N/A

Headquarters

N/A

Founded

2022

Simplify Jobs

Simplify's Take

What believers are saying

  • Expanding core team with AI Red Teamers signals scaling applied engineering services to growing demand.
  • Data Center Watch and adversarial test suites position company as infrastructure risk leader for frontier labs.
  • Aggregated third-party data and app intelligence create recurring revenue streams beyond consulting services.

What critics are saying

  • Frontier AI labs build in-house red teaming capabilities, commoditizing 10a Labs' core services within 24 months.
  • OpenAI, Anthropic, or Google launch proprietary security platforms bundling threat intelligence and compliance monitoring.
  • Loss of single Fortune 10 client representing >20% revenue due to acquisition or vendor consolidation.

What makes 10a Labs unique

  • Proprietary multilingual threat intelligence and LLM-powered content moderation systems detect abuse at scale.
  • Trusted by frontier AI labs and Fortune 10 companies for adversarial red teaming and model evaluations.
  • Integrated infrastructure risk monitoring across data centers and AI supply chains with geopolitical analysis.

Help us improve and share your feedback! Did you find this helpful?

Benefits

Company Equity

INACTIVE