AI Red Team — Penetration Testing Expert

About the Role

Your offensive security skills can directly shape how safe AI systems are for millions of people. We're hiring penetration testing experts to join AI red team engagements — probing, attacking, and stress-testing AI-powered applications and infrastructure to surface vulnerabilities before bad actors do. Fully remote, flexible contract. Offensive security meets the frontier of artificial intelligence, on high-impact projects that improve the security posture of AI systems running at scale.

Role Details

• Type: Hourly Contract
• Location: Remote
• Commitment: 10–40 hours/week
• Schedule: Independent, task-based engagements on your own time

What You'll Do

• Run penetration tests against AI-powered applications, APIs, and infrastructure to uncover vulnerabilities
• Find and exploit weaknesses across AI/ML pipelines: prompt injection, model manipulation, data poisoning vectors, authentication flaws
• Perform web application, network, and API security assessments with standard tools and methodologies
• Simulate real-world attack scenarios — reconnaissance through exploitation and post-exploitation
• Document findings in clear, structured reports with severity ratings, evidence, and actionable remediation guidance
• Evaluate AI-specific attack surfaces: adversarial inputs, jailbreaks, data exfiltration risks
• Track emerging AI security threats and feed insights back into testing methodology
• Work independently on task-based engagements, on your own schedule

Who You Are

• Experienced penetration tester grounded in offensive security principles (OWASP, PTES, MITRE ATT&CK)
• Proficient with Burp Suite, Metasploit, Nmap, Kali Linux, or equivalents
• Solid in web application, network, and API security testing
• Think like an attacker — creative, persistent, methodical at finding what others miss
• Strong writer who turns complex technical findings into clear, actionable reports
• Self-motivated and reliable working independently without direct supervision
• Comfortable across diverse technology stacks and environments

Nice to Have

• Certifications such as OSCP, OSCE, CEH, GPEN, GXPN, or eWPT
• AI/ML security testing experience — adversarial machine learning, prompt injection, LLM red-teaming
• Background in red teaming, bug bounty programs, or CTF competitions
• Cloud security (AWS, GCP, Azure) and container security familiarity
• Scripting in Python, Bash, PowerShell, or similar
• Secure development practices and DevSecOps workflow knowledge
• Security assessments in compliance-driven environments (SOC 2, ISO 27001, etc.)

Why It's Worth It

• Work on advanced AI security projects alongside leading research labs
• Fully remote and flexible — work when and where it suits you
• Freelance autonomy with access to high-impact, intellectually demanding engagements
• Sit at the front of AI security — a fast-growing field with massive demand
• Sharpen your skills against novel AI-specific attack surfaces few professionals have touched
• Help make AI systems safer and more trustworthy for users worldwide
• Potential for ongoing work and contract extension as new projects launch