Autonomous Red Team Engineer — Offensive Security & AI Agents (Equity)

NVIDIA; Virginia; Sur place; USD 224 000 - 431 000; Plein temps

Avantages offerts par ce poste

Equity

Company benefits

Résumé du poste

NVIDIA is seeking a Senior Offensive Security Engineer to push the frontier of AI-driven offensive security. You will develop autonomous red-team agents, strengthen exploit chains, and harden agent safety in a fast‑growing security org.

The role demands deep hands‑on exploitation skills, production Python, and experience with LLMs and multi‑agent orchestration. You’ll work across web, cloud/Kubernetes, and systems, collaborating with human red teams.

Qualifications

• 12+ years in security engineering with offensive security focus.
• Hands-on exploitation skills across web, cloud/Kubernetes, or systems.
• Strong Python production coding experience.
• Experience building with LLMs: agent frameworks and multi-agent orchestration.
• Sound judgment on autonomous offensive tooling and safety.

Responsabilités

• Develop red team agents for reconnaissance, exploitation, and evidence capture.
• Extend agent harnesses across runtimes and model providers.
• Encode operator tradecraft into prompts, tools, playbooks and exploits.
• Build exploit verification to reduce false positives.
• Improve safety: sandboxing, scope enforcement, and prompt-injection defenses.
• Benchmark models for offensive tasks with human teams.
• Mentor engineers and set technical standards.

Connaissances

Security engineering

Offensive security

Penetration testing

Red teaming

Python

LLM tooling

Multi-agent orchestration

Formation

Bachelor's degree or equivalent experience

Outils

Claude Code

Codex CLI

LLM frameworks

Description du poste

NVIDIA is seeking a Senior Offensive Security Engineer to push the frontier of AI-driven offensive security. You will develop autonomous red-team agents, strengthen exploit chains, and harden agent safety in a fast‑growing security org.

The role demands deep hands‑on exploitation skills, production Python, and experience with LLMs and multi‑agent orchestration. You’ll work across web, cloud/Kubernetes, and systems, collaborating with human red teams.