Senior Offensive Security Engineer, Vulnerability Operations

What you'll do

• Build autonomous and semi-autonomous LLM agents to perform reconnaissance, exploitation, and evidence capture.
• Extend agent harnesses across multiple runtimes and model providers to support multi-phase orchestration.
• Encode human red team tradecraft into prompts and tools for web, cloud, and Kubernetes attacks.
• Develop exploit-confirmation harnesses to verify findings and reduce false-positive rates.
• Engineer safety features including sandboxing, scope enforcement, and prompt-injection defenses for offensive agents.
• Benchmark frontier models for offensive tasks and convert human red team engagements into repeatable agent capabilities.
• Mentor engineers and set the technical bar for agentic offensive tooling.

What we're looking for

• 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 applications, cloud/Kubernetes, or systems/binary domains.
• Strong software engineering ability in Python to ship production code.
• Practical experience building with LLMs, including agent frameworks and multi-agent orchestration.
• Published security research, CVEs, conference talks, or notable CTF results (preferred).
• Certifications like OSWE, OSEP, OSCP, or GXPN (preferred).
• Experience red-teaming AI systems or contributing to AI-security research (preferred).