Senior Engineer, Offensive Security

Location

Selected candidate must reside within approximately 60 minutes driving distance from one of the following locations:
Louisville KY, NYC Metro, Dallas Metro, Charlotte NC Metro, South Florida (Tampa/Miami/Ft Lauderdale), Washington DC metro, Chicago, Boston, Atlanta, Nashville.

We're building a new AI & Offensive Tooling capability inside our Offensive Security organization, and we’re looking for a senior engineer who can both build it and use it. As a Senior Offensive Security Engineer, AI-Driven Red Team & Tooling, you will develop AI and agentic tooling that makes our offensive operations faster and broader, then prove it in real penetration tests, purple‑team exercises, and red‑team operations.

You will also bring that same offensive lens to the enterprise’s own AI systems.

• Build agentic offensive tooling. Write production‑quality software and AI agents, LLM‑driven planning loops, multi‑agent orchestration, and tool/function‑calling that drives real offensive tooling. Contribute to the in‑house agent platform that powers our pentest and red‑team operations, operating it as a production, event‑driven cloud platform at real scale.
• Run penetration tests. Conduct network, web‑application, cloud, and infrastructure testing, recon through exploitation, privilege escalation, and lateral movement, accelerated by the tooling you build.
• Run purple‑team exercises. Validate security countermeasures (EDR/XDR, NDR, DLP, firewalls) with our defensive partners, then pair with detection engineering to close gaps revealed by your attacks.
• Run red‑team operations and test the enterprise’s own AI. Execute objective‑driven adversary emulation and adversarial assessment of internal LLM‑powered products, agents, RAG pipelines, and ML applications to confirm guardrails and classifiers hold up.

• Build and operate (both, for real). This role explicitly lets you ship software and run engagements.
• A program serious about AI. Dedicated R&D Fridays, Hack The Box Pro Labs, role‑based paths, certification funding, and conference budgets.
• Mission that matters. Offensive Security protects the data and care of millions of people; AI is accelerating both adversary tradecraft and our own operations.

We're hiring for a genuinely hybrid skill set, real offensive operations and real AI engineering. You do not need to check every box. Depth in one half and real credibility plus a desire to grow in the other are required.

• Offensive operations experience: 4+ years in Red Team, Penetration Testing, Purple Team, or Bug Bounty with a track record of end‑to‑end engagements.
• Production Python engineering: build and operate real tooling, not one‑off scripts.
• Hands‑on with agentic AI: design, build, or operate AI agents or LLM applications, including tool/function‑calling and orchestration.
• Hands‑on testing of AI/ML systems: prompt injection, jail breaking, and adversarial techniques.
• Cloud fluency: production experience with at least one major Cloud Service Provider (AWS, GCP, or Azure).

• Built autonomous or semi‑autonomous offensive agents, LLM‑driven penetration‑testing agents, or reinforcement‑learning exploit planners.
• Red‑team tradecraft: C2 frameworks, evasion, OPSEC, and testing endpoints protected by modern EDR/XDR.
• Purple‑team fluency: MITRE ATT&CK, VECTR, Atomic Red Team.
• Experience with AI red‑team frameworks such as PyRIT…