Senior Responsible AI Researcher

Alice•San Francisco, CA

About The Position

Alice is seeking a Senior Responsible AI Researcher to lead research at the intersection of frontier models, Trust & Safety, model evaluation, and adversarial robustness. The role combines academic research with practical AI safety work, including initiating research, developing methodologies for emerging risks, and creating safety benchmarks for generative AI across text, image, multimodal, and autonomous-agent systems. The researcher will serve as a technical authority and collaborate with AI labs, academic institutions, and enterprise partners. The role also involves leading collaborative research and representing Alice at conferences and industry events; translating research findings into safety products and client-facing offerings; engaging with enterprise stakeholders; and mentoring researchers, data scientists, and engineers. The work integrates technical, social-science, policy, and product perspectives.

Requirements

PhD in Science, Technology and Society Studies (STS), Machine Learning, AI Ethics, Social Data Science, or a closely related research domain.
A strong record of peer-reviewed publications and conference presentations at top-tier venues.
Substantial experience in AI Safety, Responsible AI, Trust & Safety, or model evaluation.
Hands-on proficiency in Python and modern machine learning and deep learning frameworks such as PyTorch and Transformers.
Deep working knowledge of foundation models, including LLMs, text-to-image and multimodal models, agents, reasoning systems, and current safety mitigation techniques.
Proven experience designing datasets, benchmark suites, red-teaming protocols, or synthetic simulation platforms.
Track record of initiating research projects, developing external partnerships, and shaping technical vision.
Excellent verbal and written communication skills, including the ability to explain complex technical topics to non-technical stakeholders, executives, and research peers.
Ability to work across technical data science, social science paradigms, and product execution.

Nice To Haves

Prior employment, consulting, advisory work, or formal research collaboration with frontier AI labs or leading safety research collectives.
Experience in domain-specific safety applications such as election integrity, psychological manipulation, or agentic behavioral safety suites.

Responsibilities

Design, build, and deploy evaluation frameworks, benchmarks, and Agentic Safety Gyms to assess model capabilities, vulnerabilities, and alignment across risk domains.
Develop adversarial prompting methods, red-teaming strategies, and behavioral test suites for large language models, multimodal systems, and AI agents.
Investigate emerging risks including persuasion, manipulation, sycophancy, bias, and jailbreaking across multimodal and autonomous systems.
Lead collaborative research projects with academic institutions and industry partners.
Represent Alice at international conferences, AI safety summits, and industry events.
Publish research findings in leading AI and safety venues.
Collaborate with Product, Engineering, Go-To-Market, Policy, and Delivery teams to translate research into safety products, client offerings, and delivery methodologies.
Work with technical stakeholders and enterprise clients to turn safety and governance requirements into research questions, experiments, and evaluation suites.
Provide technical leadership and mentorship to junior researchers, data scientists, and engineers.
Integrate social science, policy, and technical perspectives into safety tools and methodologies.