Senior Red Team Engineer — AI Agent Security & Automation

Socket.dev; North Carolina; Hybrid; USD 224,000 - 431,000; Full time

Job summary

NVIDIA is seeking an experienced security engineer to craft autonomous red team agents that perform reconnaissance, exploitation, and evidence capture against targets. You will extend multi-phase agent harnesses across runtimes and model providers, encoding operator tradecraft into prompts and tools for robust offensive capabilities.

You will build verification and safety layers, mentor engineers, and evaluate frontier models for offensive tasks, turning engagements into repeatable agent

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 apps, cloud/Kubernetes, or systems.
• Strong software engineering ability in Python; production code.
• Practical experience building with LLMs: agent frameworks, tool use, multi-agent orchestration.
• Sound judgment about autonomous offensive tooling — scoping, authorization, blast-radius.

Responsibilities

• Crafting and building new red team agents: autonomous and semi-autonomous LLM agents that perform reconnaissance, hypothesis-driven exploitation, and evidence capture against NVIDIA-owned targets
• Extending our existing agent harnesses across multiple agent runtimes and model providers
• Encoding real operator tradecraft into prompts, tools, and playbooks — web app exploitation, auth bypass, SSRF/deserialization chains, cloud and Kubernetes attack paths
• Building the verification layer: exploit-confirmation harnesses that prove findings are real before a human ever sees them
• Engineering the safety side of autonomy: sandboxing, scope enforcement, tool allowlists/blocklists, credential isolation, and prompt-injection defenses
• Evaluating and benchmarking frontier models for offensive tasks; partnering with our human red team to turn their engagements into repeatable agent capabilities
• Mentoring engineers on the team and setting the technical bar for agentic offensive tooling

Skills

Security engineering

Offensive security

Penetration testing

Red teaming

Exploit development

Python

LLMs / agent frameworks

Multi-agent orchestration

Cloud/Kubernetes

Code review

Education

Bachelor's degree or equivalent experience

Tools

Claude Code

Codex CLI

Job description

NVIDIA is seeking an experienced security engineer to craft autonomous red team agents that perform reconnaissance, exploitation, and evidence capture against targets. You will extend multi-phase agent harnesses across runtimes and model providers, encoding operator tradecraft into prompts and tools for robust offensive capabilities.

You will build verification and safety layers, mentor engineers, and evaluate frontier models for offensive tasks, turning engagements into repeatable agent