As a GenAI Security Researcher, you’ll be deep diving into AI security challenges by running red teaming operations to find weaknesses in generative AI systems and their setup.

Pioneering novel bypass techniques to test the latest AI security defenses.

Identifying system flaws, driving remediation efforts, and fortifying overall AI security to help building robust, secure, and future-ready models.

Partnering with teams to automate security testing and define enterprise best practices.

Staying ahead of the curve in AI security, ethical hack

Must Have

• 2+ years in offensive cybersecurity (especially web apps and API security) OR a B.SC/M.SC. with solid AI/Cybersecurity research under your belt.
• Coding/scripting skills (like Python, JavaScript) relevant to AI security.
• A deep understanding of AI tech, especially generative models (think GPT, DALL-E, Codex, etc.).
• Solid knowledge of how AI works internally.
• Awesome problem-solving, analysis, and communication skills.

Nice to Have

• Offensive cybersecurity certs (OSWA, OSWE, OSCE3, SEC542, SEC522) OR a Master's or higher in Computer Science with a focus on Data Science or AI.
• Experience building products end-to-end, including the infrastructure and system design.
• Know-how in cloud development.
• Familiarity with AI security frameworks, compliance rules, and ethical guidelines.
• Being great at handling a super fast-paced, changing environment.

Alice is a trust, safety, and security company built for the AI era. We safeguard the communicative technologies people use to create, collaborate, and interact—whether with each other or with machines.

In a world where AI has fundamentally changed the nature of risk, Alice provides end-to-end coverage across the entire AI lifecycle. We support frontier model labs, enterprises, and UGC platforms with a comprehensive suite of solutions: from model hardening evaluations and pre-deployment red-teaming to runtime guardrails and ongoing drift detection.