Head - Research - AI Security (3-8 yrs)

Role Overview

Were seeking a visionary Head of Research - AI Security to lead our cutting-edge initiatives in adversarial machine learning, model robustness, and secure AI. You will drive high-impact research, build and mentor a world-class team, and work cross-functionally to embed research outcomes into real-world solutions.

Key Responsibilities

- Define and lead the AI Security research roadmap, focusing on adversarial ML, privacy, and model integrity.

- Build and manage a cross-functional research team across AI security and threat intelligence.

- Publish influential research and represent the organization at top-tier conferences.

- Develop and prototype defenses against attacks such as adversarial inputs, data poisoning, and model leakage.

- Collaborate with product and engineering to integrate research into security tools and platforms.

- Partner with academic institutions for joint research, fellowships, and grants.

- Advise leadership on long-term risks, AI threat landscapes, and regulatory developments.

Qualifications

- PhD (or equivalent research experience) in AI, Cybersecurity, or related fields.

- 8+ years in AI/ML research, including 4+ years in adversarial ML or secure AI.

- Proven leadership in managing research teams and translating ideas into applied security.

- Expertise in threat modeling, adversarial testing, and secure ML pipelines.

- Strong communication and collaboration skills.

Preferred Experience

- Security of LLMs, generative models, or reinforcement learning.

- Familiarity with privacy-enhancing technologies (e.g., differential privacy, federated learning).

- Contributions to open-source or published vulnerabilities in AI systems.

- Awareness of AI governance and compliance frameworks.