---
title: 'Red Teaming Fellowship at 10a Labs'
canonical: 'https://feeny.ai/job/red-teaming-fellowship-10a-labs-washington-7rdm2an2hcxd'
type: 'job'
last_seen: '2026-09-08'
---

# Red Teaming Fellowship at 10a Labs

- **Company:** 10a Labs
- **Location:** Washington, DC
- **Posted:** 2026-06-04
- **Last confirmed live:** 2026-09-08
- **Apply:** https://job-boards.greenhouse.io/10alabs/jobs/4273684009

## Job description

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.

About the role: As a Red Teaming Fellow, you will help evaluate the safety, security, and reliability of advanced AI systems. Fellows work alongside researchers, engineers, and subject-matter experts to identify vulnerabilities, uncover failure modes, and generate insights that help organizations deploy AI systems more safely.

This is a hands-on fellowship at the intersection of AI, security, and adversarial testing. Fellows will contribute to real-world evaluations of frontier models and AI-enabled systems, helping design and execute tests that probe how models behave under challenging or unexpected conditions.

In this role, you will:

- Conduct adversarial testing of AI systems across safety, security, and misuse scenarios
- Design and execute red teaming exercises against models, agents, and AI-enabled applications
- Develop prompts, attack strategies, and test cases to identify vulnerabilities and failure modes
- Analyze model behavior and document findings in clear, actionable reports
- Support the development of evaluation frameworks, taxonomies, and testing methodologies
- Research emerging AI threats, attack techniques, and risk trends
- Collaborate with engineers, researchers, and subject-matter experts to investigate emerging risks and threat vectors
- Develop front-end dashboards and other visualizations

Qualifications:

- Pursuing or recently completed a degree in Computer Science, Cybersecurity, Engineering, Data Science, Mathematics, Political Science, International Relations, or a related field
- Strong interest in AI safety, cybersecurity, red teaming, or adversarial testing
- Familiarity with AI abuse including jailbreaking, system prompt extraction, indirect prompt injection, data exfiltration, etc.
- Strong analytical, research, problem-solving, and communication skills
- Ability to think creatively from an adversarial perspective
- Ability to work independently and collaboratively in a remote environment
- Experience with Python, Bash, large language models, AI systems, cybersecurity, or research methodologies preferred
- Proficiency in a language other than English preferred

Benefits:

- Flexible start / end dates
- Remote work (based in the continental U.S.)
- Flexible schedule, up to 20 hours per week (negotiable)
- Hourly pay commensurate with experience and qualifications
- $25 per hour for undergraduate students
- $32.50 per hour for graduate students

## About 10a Labs

## Company Overview
- **One-liner**: 10a Labs is an applied research and technology company providing AI security, threat intelligence, and independent safety evaluations for frontier AI models and major technology platforms.
- **Entity Type**: Private (Privately Held)
- **Headquarters**: Washington, D.C., United States
- **Founded**: 2021
- **Founders**: Bobby McKenzie (Founder & CEO)

## Core Business
- **Primary industry**: AI Security & Safety, Threat Intelligence, Research Services
- **Target customers**: Frontier AI labs, AI unicorns, Fortune 10 companies, and leading global technology platforms (B2B, Enterprise)
- **Mission or purpose statement**: "The safety and threat-intelligence layer trusted by frontier AI labs... enabling engineering, safety, and security teams to stay ahead of evolving threats and deploy AI systems safely."

## Products & Services
- **Model Evaluations & Red Teaming**: Independent safety evaluations for frontier AI models, built for EU AI Act compliance and regulatory readiness. Includes scaled red teaming technology stress-testing generative and agentic AI systems against high-priority threats (CBRNE, Cyber Harms, Data Exfiltration, Model Distillation, Terrorism, Fraud, and more).
- **Threat Intelligence (Scout)**: Real-time monitoring for emerging threats to frontier AI systems, with proprietary threat intelligence delivered via API. Covers malicious tooling, novel abuse patterns, unauthorized access pathways, credential resale, jailbreaks, and dark web monitoring.
- **Model Defense & Integrity (Spartan)**: Advanced R&D in agentic AI systems, ML and RL model-distillation risks, and multimodal adversarial defenses to strengthen AI security and robustness.
- **Data Center Risk Analysis**: Assessment of risks to data centers stemming from geopolitical, regulatory, jurisdictional, and operational challenges.
- **Classification System**: A proprietary production ML pipeline with datasets and taxonomies informed by deep subject-matter expertise to detect emerging abuse patterns across text and other modalities.

## Market Standing
- **Valuation/Market Cap**: Not publicly available
- **Key Metric**: Total headcount of approximately 36 employees (as of mid-2025), with strong growth (+172.2% year-over-year).
- **Notable Investors/Partners**: Clients include frontier AI labs, AI unicorns, Fortune 10 companies, and leading global technology platforms. Alumni have gone on to OpenAI, Microsoft, Verizon, and other tech leaders. Talent sourced from organizations like the U.S. Department of State, Columbia SIPA, and the United Nations University.
- **Growth Signals**: Rapid headcount growth (+172.2% YoY), 32 active job postings in mid-2025, quarterly job posting growth of +166.7% and yearly growth of +3100.0%, indicating aggressive expansion across multiple departments (Research, Engineering, Threat Investigation, Data, Operations).

## Competitive Advantages
- **Specialized Focus**: A rare company fully dedicated to AI safety, security, and threat intelligence for frontier models, serving as an independent, expert safety layer.
- **Deep Expertise**: Combines subject-matter expertise (e.g., CBRNE, cyber, terrorism) with proprietary ML pipelines and red teaming technology.
- **Trusted Client Base**: Serves the most advanced AI labs and largest tech platforms, providing a unique vantage point on emerging threats.
- **Regulatory Readiness**: Built to help clients comply with frameworks like the EU AI Act, positioning them as a critical partner in the evolving regulatory landscape.

## Strategic Focus
- **Scaling the Team**: Aggressively hiring across engineering, research, threat investigation, and operations to expand capacity.
- **Advancing R&D**: Deepening research into agentic AI risks, model distillation, and multimodal adversarial defenses.
- **Global Expansion**: Posting roles in multiple regions (US, UK, Australia, France), indicating international growth.
- **Product Development**: Continuing to build out their suite of safety, intelligence, and evaluation products (Scout, Spartan, Classification System).

## Why Work Here
- **High-Impact Mission**: Work directly on ensuring the safe deployment of the world's most advanced AI systems, addressing critical security and societal risks.
- **Compelling Compensation**: Salary ranges for technical roles are highly competitive (e.g., $255K–$405K + Equity for exceptional engineers, per a recent hiring post).
- **Rapid Growth Environment**: Join a company in a strong growth phase (+172% headcount growth), offering significant opportunities for impact and career advancement.
- **On-Site Collaborative Culture**: While some roles are remote, many positions are in-office (Washington D.C., San Francisco, London), emphasizing a collaborative, hands-on work environment.
- **Strong Talent Network**: Surrounded by colleagues from top institutions and government agencies (State Department, UN, Columbia SIPA, Michigan State), fostering a culture of expertise and mission-driven work.
- **Comprehensive Roles**: Opportunities span from hands-on red teaming and software engineering to research and operations, appealing to a wide range of skills and career paths.

## Sources
1. [10alabs.com](https://10alabs.com/)
2. [Built In - 10a Labs](https://builtin.com/company/10a-labs)
3. [LinkedIn - 10a Labs](https://www.linkedin.com/company/10a-labs)
4. [Greenhouse - 10a Labs Jobs](https://job-boards.greenhouse.io/10alabs)

## Other roles at 10a Labs

- [Biosecurity & AI Safety Investigator](https://feeny.ai/job/biosecurity-ai-safety-investigator-10a-labs-remote-x8k7wrgxhsp6)
- [Software Engineer, Infrastructure & Platform](https://feeny.ai/job/software-engineer-infrastructure-platform-10a-labs-remote-z8rew4b9a2pr)
- [Cybersecurity Engineer](https://feeny.ai/job/cybersecurity-engineer-10a-labs-remote-6tw6ebfp1kh6)
- [Finance Manager - Accounting & FP&A](https://feeny.ai/job/finance-manager-accounting-fp-a-10a-labs-remote-ha9bssj2nhaa)
- [Junior Cyber Investigator](https://feeny.ai/job/junior-cyber-investigator-10a-labs-washington-tznv7eqs48aj) — Washington, DC
- [Senior Cyber Investigator](https://feeny.ai/job/senior-cyber-investigator-10a-labs-washington-a46kb0vdtmz9) — Washington, DC
- [Machine Learning Engineer](https://feeny.ai/job/machine-learning-engineer-10a-labs-remote-46rkedcxxrca)
- [AI Red Teamer, Cyber](https://feeny.ai/job/ai-red-teamer-cyber-10a-labs-washington-qhn95a7zsf7h) — Washington, DC
- [Engineering Fellowship](https://feeny.ai/job/engineering-fellowship-10a-labs-washington-wbmbw76nj2h5) — Washington, DC
- [Threat Investigator - APAC](https://feeny.ai/job/threat-investigator-apac-10a-labs-sydney-hv40zapq3bsx) — Sydney, Australia