UnitedHealth Group is looking to safeguard its AI systems, including large language models (LLMs), against adversarial and non-adversarial threats to ensure they are resilient, trustworthy, and aligned with ethical and regulatory standards, ultimately aiming to improve health outcomes by connecting people with the care, pharmacy benefits, data, and resources they need.
Requirements
- 10+ years of experience in Machine Learning and AI
- 3+ years of experience with generative AI systems (e.g., LLMs, agents) and their unique threat surfaces
- Proven experience in cybersecurity, red teaming, or adversarial and non-adversarial testing
- Knowledge of secure model deployment practices in cloud and edge environments
- Familiarity with AI safety, fairness, and interpretability frameworks
- Contributions to open-source tools, academic research, or AI security communities
Responsibilities
- Define and execute the vision and roadmap for AI red teaming initiatives across the enterprise
- Build, mentor, and lead a high-performing team of AI red teamers, adversarial ML researchers, and security engineers
- Oversee the design and execution of red teaming exercises targeting AI systems
- Partner with AI/ML engineering, enterprise cybersecurity, product, legal, and compliance teams to embed red teaming insights into model development and deployment lifecycles
- Ensure alignment with internal policies for Responsible use of AI
- Develop and operationalize robust security frameworks for large language models (LLMs) and other AI technologies
- Design and implement advanced testing methodologies-including red teaming, adversarial simulations, and model robustness evaluations-to identify vulnerabilities
Other
- 6+ years of leadership experience managing technical teams and cross-functional initiatives
- Proven solid communication skills with the ability to influence executive stakeholders and translate technical findings into business impact
- Experience working in regulated industries (e.g., finance, healthcare, defense) with AI governance requirements
- Flexibility to work remotely from anywhere within the U.S.
- Candidates are required to pass a drug test before beginning employment.
