AI Red Teamer, Cyber

10a Labs•Washington, DC

8d•$100,000 - $120,000•Remote

About The Position

10a Labs is seeking an AI Red Teamer with deep cybersecurity expertise to help evaluate the security and resilience of advanced AI systems and applications. This role is ideal for someone who enjoys offensive security, creative problem-solving, and thinking like an adversary. In this role, you will design and execute red team assessments against AI systems, applications, and supporting infrastructure, translate ambiguous objectives into structured testing plans and attack strategies, develop adversarial testing methodologies to evaluate system security, robustness, and resilience, craft prompts, attack chains, and adversarial inputs to uncover unintended or unsafe system behavior, identify vulnerabilities, security risks, and failure modes through testing and analysis, analyze system outputs and behaviors to assess security and safety risks, document findings, communicate risk, and provide actionable recommendations, collaborate with engineers, researchers, and subject-matter experts to improve system security, and continuously refine testing methodologies based on emerging threats and attacker techniques.

Requirements

Degree in Computer Science, Engineering, Cyber Security, or a related field (or equivalent practical experience)
Strong understanding of cybersecurity principles, attack methodologies, and common vulnerability classes
Experience with security tools such as Splunk, Wireshark, Metasploit, Burp Suite, Nmap, or similar platforms
Comfortable working in Linux and terminal-based environments
Experience scripting or automating workflows using Python, Bash, or similar languages
Familiarity with SIEM platforms and security monitoring concepts
Ability to think creatively from an adversarial perspective and investigate complex technical problems
Excellent analytical and problem-solving skills
Excellent written and verbal communication skills

Nice To Haves

CompTIA Security+ certification and/or Google Cybersecurity Certificate
Experience testing AI, machine learning, or large language model applications
Familiarity with prompt injection, jailbreak techniques, or other AI attack methodologies
Offensive security certifications such as PNPT, OSCP, CySA+, GCIH, or GPEN
Experience supporting government, defense, intelligence, or critical infrastructure environments

Responsibilities

Design and execute red team assessments against AI systems, applications, and supporting infrastructure
Translate ambiguous objectives into structured testing plans and attack strategies
Develop adversarial testing methodologies to evaluate system security, robustness, and resilience
Craft prompts, attack chains, and adversarial inputs to uncover unintended or unsafe system behavior
Identify vulnerabilities, security risks, and failure modes through testing and analysis
Analyze system outputs and behaviors to assess security and safety risks
Document findings, communicate risk, and provide actionable recommendations
Collaborate with engineers, researchers, and subject-matter experts to improve system security
Continuously refine testing methodologies based on emerging threats and attacker techniques