Senior Offensive Security Engineer, Vulnerability Operations

NVIDIA

Senior Offensive Security Engineer advancing NVIDIA's AI-driven vulnerability operations. Building autonomous red team agents, exploit verification, and safety controls for large-scale offensive security.

Posted 9/3/2026full-timeRemote • California, Colorado, North Carolina, Texas, Virginia • 🇺🇸 United StatesSenior💰 $224,000 - $431,250 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates extensive expertise in offensive security engineering, particularly in penetration testing and red teaming, with a strong focus on building and mentoring autonomous LLM agents. Proficient in Python and experienced in developing security tools and frameworks for web applications, cloud environments, and Kubernetes.

Highest-signal resume keywords

Offensive Security EngineeringPython Software EngineeringLLM Agent DevelopmentPenetration TestingSecurity Research Publication

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Exploitation SkillPenetration TestingRed TeamingVulnerability ResearchMulti-Agent OrchestrationFuzzingProgram AnalysisCloud SecurityWeb Application SecuritySystems/Binary Exploitation

Soft Skills

Sound JudgmentRespectful ApproachMentoring

Tools & Technologies

KubernetesOpenShiftGitOpsLLM FrameworksAgent Frameworks

Certifications & Qualifications

OSWEOSEPOSCPGXPN

Industry Keywords

Autonomous Offensive ToolingExploit-Confirmation HarnessesSASTDASTAI-Security Research

Tech Stack

Tools & technologies

CloudKubernetesOpenShiftPython

About the role

Key responsibilities & impact

Craft and build autonomous and semi-autonomous LLM red team agents for reconnaissance, hypothesis-driven exploitation, and evidence capture against NVIDIA-owned targets
Extend agent harnesses with multi-phase orchestration, parallel specialist subagents, judge/verifier stages, and out-of-band callback infrastructure
Encode offensive security tradecraft into prompts, tools, and playbooks across web application, cloud, Kubernetes, and related attack paths
Build exploit-confirmation harnesses to validate findings and reduce false positives
Engineer safety controls including sandboxing, scope enforcement, tool allowlists/blocklists, credential isolation, and prompt-injection defenses
Evaluate and benchmark frontier models for offensive tasks
Partner with the human red team to convert engagements into repeatable agent capabilities
Mentor engineers and set the technical bar for agentic offensive tooling

Requirements

What you’ll need

Bachelor's degree or equivalent experience
12+ years in security engineering, with at least 4 years in offensive security: penetration testing, red teaming, exploit development, or vulnerability research
Deep, hands-on exploitation skill in at least one domain: web application, cloud/Kubernetes, or systems/binary
Strong software engineering ability in Python; production code experience
Practical experience building with LLMs: agent frameworks, tool use/function calling, multi-agent orchestration, or coding agents (Claude Code, Codex CLI, or similar)
Sound judgment about autonomous offensive tooling, including scoping, authorization, and blast-radius thinking
Respectful, responsible approach to offensive testing
Published security research, CVEs, conference talks, or notable CTF results
Certifications such as OSWE, OSEP, OSCP, or GXPN
Experience with SAST/DAST internals, fuzzing, or program analysis
Experience red-teaming AI systems or contributing to AI-security research
Familiarity with Kubernetes/OpenShift, GitOps, and operating worker fleets at scale

Benefits

Comp & perks

Competitive salaries
Generous benefits package
Equity