Vulnerability Researcher for AI Security

Operate as an internal adversary who discovers novel attack paths across AI agents, cloud infrastructure, developer platforms, and production systems. In this core team role at micro1, you will perform advanced offensive research to harden our stack, partner with engineering teams to validate fixes and improve secure-by-design practices, and publish findings that shape long-term security strategy.

• Conduct advanced offensive security research across cloud infrastructure, production services, internal tooling, and AI platforms.
• Design and execute realistic adversary simulations targeting identity systems, cloud control planes, supply chains, and distributed architectures.
• Discover and exploit vulnerabilities in proprietary applications, APIs, infrastructure-as-code, CI/CD pipelines, and AI-powered developer workflows.
• Research emerging attack vectors against LLMs, AI agents, retrieval systems, multi-component integrations, prompt orchestration, and autonomous workflows.
• Reverse engineer critical services to uncover architectural weaknesses, novel exploitation techniques, and previously unknown vulnerability classes.
• Simulate insider and advanced persistent threat scenarios, evaluating privilege escalation, lateral movement, and defense evasion across modern enterprise environments.
• Build custom offensive tooling, automation frameworks, fuzzers, and proof-of-concept exploits to accelerate vulnerability discovery.
• Partner closely with infrastructure, product, and AI engineering teams to validate fixes and improve security practices.
• Document attack methodologies, publish internal research, and help shape the organization''s security roadmap.

Required

• Proven experience in offensive security, vulnerability research, red teaming, or exploit development.
• Deep understanding of cloud security across AWS and GCP, including IAM, networking, Kubernetes, containers, and identity systems.
• Strong background in application security, code auditing, reverse engineering, and vulnerability discovery.
• Experience identifying weaknesses across software supply chains, CI/CD systems, APIs, and infrastructure automation.
• Proficiency in one or more of Python, Go, Rust, C, or C++ for security research and tooling.
• Strong understanding of operating system internals, networking, authentication protocols, and modern security architectures.
• Ability to investigate ambiguous problems independently and develop novel attack techniques.
• Excellent written communication skills, able to explain complex vulnerabilities to engineering teams.

Preferred

• Research experience in AI and LLM security, including agentic systems, prompt injection, tool abuse, indirect prompt attacks, jailbreaks, retrieval-augmented generation security, or autonomous workflows.
• Experience discovering zero-day vulnerabilities or developing exploits.

• Location: Remote.
• Employment type: Full-time.
• Role sits on the core vulnerability research team and partners with engineering across the organization.

USD 240, 000 to 400, 000 per year.