Senior Genai Safety Researcher

### Description Alice is seeking a driven, detail-focused **Senior Generative AI Researcher** to take on a leading role within our US team. In this position, you will operate at the cutting edge of AI Safety and Trust & Safety, analyzing potential vulnerabilities and content safety risks across the newest wave of Generative AI tools. As a Senior Researcher, you won't just run tests, you will **design robust testing methodologies,** act as a **core content expert** to support the Program Lead, and actively **expand the team’s internal knowledge base.** You will partner closely with cross-functional teams and external stakeholders to secure models across multiple modalities, including LLMs, Text-to-Image, Text-to-Video, and AI Agents. ### Key Responsibilities ### Methodology & Strategy * Architect rigorous, scalable testing methodologies and red-teaming frameworks to evaluate foundational models, multimodal systems, and AI agents. * Develop sophisticated prompt strategies across diverse risk domains (e.g., Hate Speech, Misinformation, IP & Copyright infringement, Child Safety) to expose complex model vulnerabilities. * Conduct ongoing research into emerging jailbreak tactics, prompt injection techniques, and novel circumvention strategies used against foundational safety measures. ### Subject-Matter Expertise * Serve as a trusted content and domain expert, providing deep technical and policy insight to support the Program Lead in scoping projects, assessing risks, and driving strategy. * Lead efforts to continuously document, synthesize, and expand Alice’s internal AI Safety knowledge base, standardizing best practices, taxonomies, and research findings across the team. * Mentor junior analysts, foster a culture of continual learning, and elevate the team’s analytical standards. ### Operational Excellence * Own engagement lifecycles from initial planning and methodology design through execution, quality assurance (QA), and final delivery. * Oversee complex, multi-language datasets across multiple areas of abuse, ensuring the highest precision, accuracy, and output quality. * Partner effectively with engineering, product, policy, and client-facing teams to communicate research findings and inform mitigation strategies. ### Requirements ### Must-Have * **5+ years of experience** in AI Safety, Responsible AI, Trust & Safety, or aligned research domains. * **Proven expertise in research design** and building qualitative or quantitative evaluation methodologies for GenAI. * **Strong domain expertise** in content risks (e.g., toxicity, copyright, misinformation, safety policy violations). * **Track record of project ownership,** leading deliverables end-to-end with high attention to detail in fast-paced, variable environments. * **Deep familiarity with modern Generative AI architectures,** prompt engineering, red-teaming, and AI agents. * **Strong communication skills** to act as a core subject-matter contact for program leads, internal teams, and clients. ### Nice-to-Have * Proven track record of published research in academia, industry whitepapers, or a research institute. * Hands-on experience evaluating multimodal systems (Text-to-Image, Text-to-Video, Audio). * Experience mentoring, leading, or QAing the work of junior analysts and researchers. The salary range for this role is $105K - $115K OTE - Range may vary based on experience. Salary at the time of offer will be commensurate with experience. ### 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. Originally posted on [Himalayas](https://himalayas.app)