Autonomous Red Team Engineer — Offensive Security

NVIDIA; United States; Remote; USD 224,000 - 431,000; Full time

Benefits offered by this job

Equity

Job summary

NVIDIA's Product Security organization seeks a Senior Offensive Security Engineer to push AI-driven offensive security forward. You will build autonomous red team agents, extend multi-agent harnesses, and craft exploit chains across web, cloud, and systems domains.

You will mentor engineers, evaluate frontier models, and ensure safe autonomy with robust sandboxing and scope controls. Base salaries range widely by level, with equity and benefits offered.

Qualifications

• Bachelor's degree or equivalent experience.
• 12+ years in security engineering, with at least 4 years in offensive security.
• Deep, hands-on exploitation skill in web app, cloud/Kubernetes, or systems/binary.
• Strong software engineering ability in Python; production code.
• Experience building with LLMs: agent frameworks, tool use, multi-agent orchestration.
• Sound judgment on autonomous offensive tooling and safe scope.

Responsibilities

• Crafting and building new red team agents for reconnaissance and exploitation against NVIDIA-owned targets.
• Extending multi-phase orchestration harnesses across runtimes and model providers.
• Encoding operator tradecraft into prompts, tools, and playbooks for various attack paths.
• Building the verification layer to prove findings before human review.
• Engineering the safety side of autonomy: sandboxing, scope enforcement, and isolation.
• Evaluating frontier models for offensive tasks and collaborating with humans to scale capabilities.
• Mentoring engineers and setting technical standards for agentic tooling.

Skills

Offensive security

Red teaming

Penetration testing

Exploit development

Vulnerability research

Python

LLM integration

Education

Bachelor's degree

Tools

Claude Code

Codex CLI

Agent frameworks

Kubernetes/OpenShift

Job description

NVIDIA's Product Security organization seeks a Senior Offensive Security Engineer to push AI-driven offensive security forward. You will build autonomous red team agents, extend multi-agent harnesses, and craft exploit chains across web, cloud, and systems domains.

You will mentor engineers, evaluate frontier models, and ensure safe autonomy with robust sandboxing and scope controls. Base salaries range widely by level, with equity and benefits offered.