AI Security Penetration Tester / AI Red Team Engineer

AI Security Penetration Tester / AI Red Team Engineer

Dice is the leading career destination for tech experts at every stage of their careers. Our client, Virtuous Tech Inc, is seeking a highly skilled professional to lead offensive security engagements focused on AI/ML-powered applications and platforms.

Position Overview

In this role, you will identify, exploit, and demonstrate security risks across traditional and AI-specific attack surfaces, including LLMs, AI-enabled APIs, and AI-driven business logic. You will work alongside Engineering, Security, Red Teams, SOC, and AI research teams to simulate realistic AI attacks and guide remediation strategies.

Key Responsibilities

• Conduct AI-focused penetration testing on web, API, mobile, and AI-powered systems.
• Perform red teaming exercises including prompt injection, jailbreak testing, model evasion, and adversarial ML attacks.
• Identify risks like model poisoning, data leakage, adversarial inputs, and AI business logic abuse.
• Execute threat modeling and architecture reviews for AI-enabled applications.
• Develop and enhance AI-focused offensive security tools and methodologies.
• Research emerging AI attack techniques for business impact assessment.
• Deliver comprehensive penetration testing reports and executive presentations.
• Lead end-to-end engagements including scoping, execution, reporting, and remediation.
• Partner with engineering teams to provide actionable security recommendations.
• Collaborate with Red Teams and SOC to improve AI security playbooks.

Required Qualifications

• 3+ years of penetration testing experience (web, API, mobile).
• Proven experience in AI red teaming, LLM security testing, or adversarial ML.
• Proficiency with tools like Burp Suite Pro, Netsparker, and Checkmarx.
• Working knowledge of AI/ML frameworks such as TensorFlow, PyTorch, LLM APIs, and LangChain.
• Strong understanding of OWASP Top 10, API security, and modern attack vectors.
• Excellent communication skills.
• Relevant security certifications (GWAPT, OSWE, OSWA, CREST, etc.) preferred.
• Bachelor’s degree in Computer Science, Cybersecurity, or equivalent experience.

Preferred Qualifications

• Experience testing LLM-based applications, chatbots, copilots, or AI workflows.
• Familiarity with MLOps, model deployment security, and cloud AI platforms (AWS, Azure, Google Cloud Platform).
• Ability to build custom offensive tools/scripts in Python, Go, or similar languages.
• Exposure to SOC operations, detection engineering, or purple team exercises.
• Contributions to AI security research, blogs, talks, or open-source projects.

What Success Looks Like

• AI vulnerabilities identified before production release.
• Clear demonstration of AI attack paths and business risk.
• Actionable remediation guidance adopted by engineering teams.
• Continuous evolution of AI red teaming methodologies.
• Measurable improvement in the enterprise AI security posture.

Key Skills/Competency

• Penetration Testing
• Red Teaming
• AI Security
• Adversarial ML
• LLM Security
• Threat Modeling
• Vulnerability Assessment
• Security Tools
• Risk Analysis
• Remediation