Senior AI Security Researcher

This is a fully remote position, open to applicants in North Carolina, +3 more states.

📋 Description

• Formulate and respond to open-ended AI security research inquiries that assist NVIDIA in understanding, assessing, and mitigating risks associated with frontier models, agentic systems, AI platforms, and AI-enabled products.

• Create practical methods, prototypes, evaluations, or tools that expose how AI systems may fail in adversarial scenarios and identify ways to mitigate those risks.

• Investigate a variety of AI security challenges, including LLM and agent security, adversarial testing, model evaluation, cyber-defense automation, vulnerability identification, secure deployment, and autonomous response.

• Convert research findings into actionable results for engineering and security teams, including proof-of-concept demonstrations, benchmarks, technical guidance, mitigations, and recommendations for secure-by-design practices.

• Collaborate across offensive security, product security, AI research, platform, cloud, and infrastructure teams to align research insights with NVIDIA's most critical security objectives.

• Contribute to shaping NVIDIA's AI-security research strategy by mentoring others, recognizing emerging risks, and establishing repeatable practices for the assessment and defense of AI systems.

⛳️ Requirements

• Over 12 years of experience in AI security, cybersecurity research, applied ML research, offensive security, cyber defense, or related technical domains.

• Proven track record of original research and practical impact, such as implemented security ML systems, AI-security assessments, CVEs, patents, publications, conference presentations, open-source tools, production mitigations, or funded research initiatives.

• Proficient in developing functional research systems using Python and contemporary ML/data tools like PyTorch, JAX, TensorFlow, scikit-learn, Pandas, NumPy, Spark, BigQuery, or similar platforms.

• Familiarity with one or more areas of AI security: LLM security, adversarial ML, model evaluation, agent security, prompt injection, model backdoors, data poisoning, model misuse, secure RAG, synthetic data, or AI-enabled security automation.

• Strong foundation in cybersecurity, including threat modeling, adversary simulation, exploit or vulnerability research, malware analysis, network defense, threat hunting, detection engineering, digital forensics, secure code review, or incident-response automation.

• Capability to navigate ambiguous research challenges and practical product limitations, translating findings into prioritized recommendations and measurable security outcomes.

• Bachelor's degree or equivalent experience in Computer Science, Machine Learning, Cybersecurity, or a related field.

• Experience leading AI-security research for significant models, AI platforms, security products, or large-scale production systems.

🏝️ Benefits

• equity

• benefits