Senior Autonomous Red Team Engineer – Offensive Security

NVIDIA; Santa Clara (CA); On-site; USD 224,000 - 431,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA's Product Security organization is seeking a Senior Offensive Security Engineer to push the frontier of AI-driven offensive security. You will build and operate autonomous red team agents that audit live targets at fleet scale, shaping new attack capabilities and verification methods.

You will mentor engineers, extend our agent harnesses across runtimes and model providers, and implement safety controls. This is a hands-on role for a practitioner who can both break and secure systems.

Qualifications

• Bachelor's degree or equivalent experience.
• 12+ years in security engineering with 4+ years offensive security.
• Hands-on exploitation in at least one domain (web, cloud/Kubernetes, or systems).
• Strong Python software engineering experience; production code.
• Experience building with LLMs: agent frameworks, multi-agent orchestration.
• Sound judgment on autonomous offensive tooling: scoping and safety.
• Respectful approach to offensive testing and rapid fixes.

Responsibilities

• Build autonomous red team agents for reconnaissance and exploitation.
• Extend agent harnesses across runtimes and model providers.
• Encode operator tradecraft into prompts, tools, and playbooks for web, auth bypass, and cloud paths.
• Develop exploit-verification harnesses to reduce false positives.
• Implement sandboxing, scope enforcement, and prompt-injection defenses for agents.
• Benchmark frontier models for offensive tasks with human teams.
• Mentor engineers and set technical standards for tooling.

Skills

Python

Penetration testing

Red teaming

Exploit development

Cloud/Kubernetes

LLM agents

Software engineering

Agent orchestration

Education

Bachelor's degree or equivalent experience

Tools

Kubernetes

Job description

NVIDIA's Product Security organization is seeking a Senior Offensive Security Engineer to push the frontier of AI-driven offensive security. You will build and operate autonomous red team agents that audit live targets at fleet scale, shaping new attack capabilities and verification methods.

You will mentor engineers, extend our agent harnesses across runtimes and model providers, and implement safety controls. This is a hands-on role for a practitioner who can both break and secure systems.