Senior Offensive Security Engineer, Vulnerability Operations

This is a fully remote position, open to applicants in California, +4 more states.

📋 Description

• Develop and construct autonomous and semi-autonomous LLM red team agents designed for reconnaissance, hypothesis-driven exploitation, and evidence collection against NVIDIA-owned assets.

• Enhance agent frameworks with multi-phase orchestration, parallel specialized subagents, judge/verifier stages, and out-of-band callback systems.

• Integrate offensive security methodologies into prompts, tools, and playbooks across web applications, cloud environments, Kubernetes, and other relevant attack vectors.

• Create exploit-confirmation frameworks to verify findings and minimize false positives.

• Design safety measures, including sandboxing, scope enforcement, tool allowlists/blocklists, credential isolation, and defenses against prompt injection.

• Assess and benchmark cutting-edge models for offensive operations.

• Collaborate with the human red team to transform engagements into repeatable agent capabilities.

• Guide engineers and establish the technical standards for agent-based offensive tools.

⛳️ Requirements

• Bachelor’s degree or equivalent experience.

• Over 12 years in security engineering, with a minimum of 4 years in offensive security, including penetration testing, red teaming, exploit development, or vulnerability research.

• Extensive, hands-on exploitation expertise in at least one area: web applications, cloud/Kubernetes, or systems/binary.

• Strong software engineering skills in Python, with experience in production-level code.

• Practical background in working with LLMs: agent frameworks, tool utilization/function calling, multi-agent orchestration, or coding agents (Claude Code, Codex CLI, or similar).

• Good judgment regarding autonomous offensive tools, including scoping, authorization, and blast-radius considerations.

• A respectful and responsible approach to offensive testing.

• Published security research, CVEs, conference presentations, or notable CTF achievements.

• Relevant certifications such as OSWE, OSEP, OSCP, or GXPN.

• Experience with SAST/DAST internals, fuzzing, or program analysis.

• Familiarity with red-teaming AI systems or contributing to AI-security research.

• Knowledge of Kubernetes/OpenShift, GitOps, and managing worker fleets at scale.

🏝️ Benefits

• Competitive salaries.

• Generous benefits package.

• Equity.