10a Labs
AI Red Teamer, Cyber
$100K–$120K
Washington DC +1 · Full-time · Posted Jun 1, 2026
- Location
- Washington DC
10a Labs - Experience
- 2–5 years of relevant professional experience.
- Education
- Degree in Computer Science, Engineering, Cyber Security, or a related field (or equivalent practical experience).
About the job
Conduct offensive security assessments of AI systems and supporting infrastructure, identify vulnerabilities and safety risks, and recommend improvements.
What you'll do
- Design and execute red-team assessments and develop adversarial testing plans and methodologies.
- Craft prompts, attack chains, and adversarial inputs; analyze behavior to identify vulnerabilities, risks, and failure modes.
- Document findings, recommend actions, and collaborate with engineers and researchers to improve security.
What they ask for
- 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; familiarity with SIEM and security monitoring concepts.
- Comfort with Linux and terminal environments, plus scripting or workflow automation using Python, Bash, or similar languages.
Nice to have
- CompTIA Security+ and/or Google Cybersecurity Certificate; offensive security certifications such as PNPT, OSCP, CySA+, GCIH, or GPEN.
- Experience testing AI, machine learning, or large language model applications; familiarity with prompt injection, jailbreaks, or other AI attack methodologies.
Pay
$100K–$120K (base salary)
Tools
Splunk, Wireshark, Metasploit, Burp Suite, Nmap, Linux, Python, Bash
AI focus
Red-team and evaluate the security, robustness, resilience, and safety of AI systems and applications using adversarial prompts, attack chains, and testing methodologies.
Model-written summary · the original posting is authoritative