The AI Red Team Engineer role focuses on identifying and mitigating AI-native security risks in products and internal platforms. This position combines offensive security with AI engineering, emphasizing behavioral and contextual attacks on AI systems. The engineer will work closely with AI platform teams and product engineers to develop defenses against potential vulnerabilities. Ideal candidates will have a strong understanding of AI systems and enjoy thinking like an attacker.

• 3+ years of experience in security engineering, offensive security, red teaming, or AI security.
• Hands-on experience red-teaming AI models or AI agents, including testing for prompt injection and unsafe behavior.
• Strong understanding of security fundamentals such as threat modeling and secure design.
• Ability to clearly document findings and communicate risk to both technical and non-technical stakeholders.
• Proficiency in at least one programming language such as Python, Go, or Java.

• Design and execute AI red-teaming exercises against LLMs and AI agents.
• Analyze agent workflows, logic, and tool graphs to identify systemic security weaknesses.
• Develop reusable adversarial test cases, attack libraries, and red-team playbooks for AI systems.
• Collaborate with AI platform and product teams to translate red-team findings into actionable mitigations.

• Employees at Uber are often offered comprehensive health, life, disability, and mental wellness benefits, along with wellbeing stipends, travel medical coverage, and monthly Uber credits for Rides and Eats. Employees also get generous paid parental leave, flexible time off, and family-planning support so they can care for themselves and their families at every stage.