As our AI Agents Security Team Leader, you’ll have the unique opportunity to build and lead a small, high-impact team of researchers and developers at the cutting edge of AI and security. You'll work hands-on, solving novel problems and architecting the foundational security systems for intelligent agents with plenty of room to innovate and make your mark.

What You'll Do

• Lead & Inspire: Mentor and guide a team of researchers and developers passionate about securing AI-driven systems.
• Build Security Solutions: Design, develop, and deploy security frameworks and tools tailored to LLMs, autonomous agents, and multi-agent environments.
• Defend the Frontier: Proactively identify vulnerabilities, conduct red-team exercises, and develop solutions to protect against state-of-the-art threats such as adversarial attacks, model inversion, and data leakage.
• Stay Lean & Agile: Thrive in a fast-moving start-up, balancing hands-on technical work with strategic decision-making.
• Collaborate Cross-Functionally: Work closely with AI researchers, product leaders, and founders to integrate security into every aspect of our technology stack.
• Shape the Future: Keep pace with emerging research and threats, and help set the direction for AI security in an entrepreneurial environment.

What We're Looking For

• Proven experience (4+ years) in cybersecurity, including 2+ years in a technical leadership role.
• Hands-on skills in Python, C++ or similar, and confidence in secure software engineering.
• Understanding of AI/ML security concepts—experience with open-source frameworks like PyRIT, Garak and OWASP GenAI Top10.
• Strong knowledge of current security practices, cloud solutions, adversarial ML, and threat modeling for advanced AI systems.
• Track record of thriving in fast-paced, ambiguous startup or early-stage environments.
• Clear, collaborative communicator who gets excited about mentoring and growing with a passionate team.
• A startup mindset: adaptable, proactive, and eager to learn and innovate.

Bonus

• Strong background in Offensive Security (Application penetration testing and red teaming).
• Certifications (CISSP, CEH, OSCP) or background in AI ethics and responsible AI.
• Publications or open-source contributions in AI security.

DeepKeep champions diversity and inclusivity. We encourage qualified individuals of all races, colors, religions, sexes, ages, national origins, physical or mental disabilities, veteran statuses, or any other characteristic protected by law to apply.

‍