Senior Offensive Security Engineer, Vulnerability Operations

What you'll do

• Build autonomous and semi-autonomous LLM agents for reconnaissance, exploitation, and evidence capture against internal targets.
• Expand existing agent harnesses across multiple runtimes and model providers to improve multi-phase orchestration.
• Encode human red team tradecraft into prompts and tools for web, cloud, and Kubernetes attack paths.
• Develop exploit-confirmation harnesses to verify findings and reduce false-positive rates before human review.
• Engineer safety controls including sandboxing, scope enforcement, and prompt-injection defenses for autonomous agents.
• Benchmark frontier models for offensive tasks by converting manual red team engagements into repeatable agent capabilities.
• Mentor engineers and set the technical standards for agentic offensive security tooling.

What we're looking for

• Bachelor's degree or equivalent experience.
• 12+ years of experience in security engineering.
• At least 4 years of experience in offensive security including penetration testing, red teaming, exploit development, or vulnerability research.
• Deep, hands-on exploitation skills in web applications, cloud/Kubernetes, or systems/binary domains.
• Strong software engineering ability to ship production code in Python.
• Practical experience building with LLMs using agent frameworks, tool use, and multi-agent orchestration.
• Experience red-teaming AI systems, including prompt injection and model evaluation.
• Relevant certifications such as OSWE, OSEP, OSCP, or GXPN.