AI Security Engineer / Offensive Security Engineer

About the role

Our client is looking for a highly hands‑on security engineer to continuously attack, test, and strengthen their AI product and infrastructure. This person should think like a white‑hat hacker: spend meaningful time trying to break the system, identify vulnerabilities across agents, APIs, identity, memory, permissions, data flows, and infrastructure, then work directly with engineering to understand, prioritize, and fix what they find.

Key responsibilities

• Continuously red‑team the company's product, infrastructure, APIs, and agentic systems; identify and reproduce vulnerabilities, then partner with engineers through remediation.
• Test AI‑specific attack surfaces including prompt injection, tool misuse, data leakage, permission escalation, memory poisoning, and unsafe agent behavior.
• Use agents, automation, and security tooling to continuously probe systems and surface weaknesses.
• Triage findings based on exploitability, user impact, and business risk.
• Strengthen authentication, authorization, identity, secrets management, data boundaries, and infrastructure security.
• Build lightweight monitoring, testing, and defensive systems that improve continuously as the product evolves.
• Help establish pragmatic security standards and development practices without introducing unnecessary process.

Required profile

• Strong experience in application, product, cloud, or offensive security with 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 coding ability to build security tooling, automation, and fixes.
• Familiarity with AI/LLM security risks and strong interest in securing agentic systems.
• Comfortable operating in a fast‑moving, zero‑to‑one environment where the security model evolves alongside the product.
• Pragmatic judgment: knows established security best practices, applies them well, and knows when deeper investigation is warranted.
• Experience red‑teaming LLM or agent systems, building automated security testing infrastructure, or working on products involving sensitive identity, memory, permissions, or user data is a plus.
• Located in Latin America and fluent English.

What we offer

• 100% Remote Work: work from any location with a laptop and reliable internet.
• Highly Competitive USD Pay: market‑leading compensation in US dollars.
• Paid Time Off: policies to unwind and recharge.
• Work with Autonomy: freedom to manage time as long as results are delivered.
• Work with Top American Companies: engage on innovative, high‑impact projects for industry‑leading U.S. firms.