Job Description

ALICE is looking for a Senior Generative AI Analyst (Red Team) to help secure the next generation of AI systems. In this role, you will lead advanced safety red-teaming efforts to identify risks, vulnerabilities, and failure modes in Generative AI models, including LLMs, text-to-image, and emerging modalities.

You’ll work at the intersection of technology, policy, and real-world risk, collaborating with internal teams, external experts, and clients to design rigorous, defensible testing strategies and deliver high-quality safety insights.

What You’ll Do

• Design and execute advanced red-teaming and adversarial testing of Generative AI systems
• Develop adversarial prompts to probe model weaknesses across multiple risk domains
• Analyze and communicate model vulnerabilities and safety insights
• Ensure high standards of data quality, documentation, and traceability
• Collaborate with multidisciplinary teams and external specialists
• Contribute to red-teaming tools, methodologies, and infrastructure
• Engage with clients and stakeholders as a subject-matter expert

Requirements

• Command of English at a near-native level.
• Experience in AI safety evaluation, red-teaming, or advanced model testing
• Strong understanding of Generative AI risks and sociotechnical failure modes
• Solid technical knowledge of modern AI systems, especially LLMs
• Ability to design and defend robust testing methodologies
• Excellent analytical and communication skills
• Comfort working autonomously in fast-moving, ambiguous environments

About Alice

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.