Role OverviewThe role involves continuously attacking, testing, and strengthening the client's AI product and infrastructure. The candidate should think like a white-hat hacker, identifying vulnerabilities across agents, APIs, identity, memory, permissions, data flows, and infrastructure, then work directly with engineering to understand, prioritize, and fix what they find.
What You Will Do
The day-to-day responsibilities include orchestrating agents to probe the system, investigating suspicious behavior or failure modes, reproducing exploits, hardening production systems, and gradually building an iterative defensive security layer around the product.
Why It Might Be a Fit
The ideal person combines an offensive security mindset with strong engineering judgment, someone who enjoys breaking systems as much as fixing them, can distinguish theoretical risk from meaningful product risk, and can help make security an ongoing engineering practice rather than a periodic audit.
Requirements
- Strong experience in application, product, cloud, or offensive security.
- Hands-on ability to identify, exploit, debug, and remediate vulnerabilities.
- Solid understanding of modern web architecture, APIs, authentication/authorization, cloud infrastructure, and data security.
- Strong engineering fundamentals and enough coding ability to build security tooling, automation, and fixes.
- Familiarity with AI/LLM security risks and strong interest in securing agentic systems.
- Pragmatic judgment: knows established security best practices, applies them well, and knows when deeper investigation is actually warranted.
Benefits
- 100% Remote Work
- Highly Competitive USD Pay
- Paid Time Off
- Work with Autonomy
- Work with Top American Companies
]]>