Build the AI agents and orchestration that power autonomous penetration testing — turning LLM reasoning and deterministic tooling into reliable, real-world exploit discovery.
What you'll do
- Design and ship multi-agent systems that plan, execute, and validate security tests.
- Integrate LLMs with offensive tooling, proxies, and deterministic validators.
- Improve agent reliability, evaluation, and guardrails at scale.
- Collaborate with security researchers to encode their expertise into automation.
What we're looking for
- 3+ years building production software, including LLM or agent frameworks.
- Strong Python and systems-design skills.
- Familiarity with prompt engineering, tool-use, and evaluation pipelines.
- Bonus: a security background or genuine interest in offensive tooling.
Apply for this role
Send your CV and a short intro to contact@strike7.ai.