Principal AI Research Cybersecurity Scientist (Bay Area)

Alice • San Francisco, CA

4d

About The Position

Alice is seeking a highly technical, hands-on Principal AI Research Cybersecurity Scientist to drive fast-paced research in frontier AI models, benchmarking, and evaluation. The role combines strong research credentials with exceptional engineering capabilities and the ability to execute rapid research cycles—from identifying research questions to building prototypes, running experiments, and delivering actionable results. It requires deep expertise in LLMs, foundation models, reasoning, agents, and model evaluation, as well as the ability to translate complex customer challenges into measurable research outcomes.

Alice is a trust, safety, and security company focused on the AI era. It provides end-to-end coverage across the AI lifecycle for frontier model labs, enterprises, and UGC platforms, including model-hardening evaluations, pre-deployment red-teaming, runtime guardrails, and ongoing drift detection.

Requirements

• PhD or MSc in Computer Science, AI, Machine Learning, or a related field, with strong relevant research experience.
• Strong publication record at leading AI/ML conferences such as NeurIPS, ICML, ICLR, ACL, or equivalent venues.
• Advanced Python and PyTorch skills, with experience building and evaluating complex AI systems.
• Ability to independently design, implement, and execute research experiments within short development cycles.
• Deep understanding of LLMs, foundation models, benchmarking, and evaluation methodologies.
• Strong analytical and communication skills, with the ability to work effectively in a fast-paced, customer-driven research environment.

Nice To Haves

• Experience with frontier AI labs such as OpenAI, Anthropic, or Google DeepMind.
• Experience with AI for Cybersecurity, including autonomous security agents, vulnerability research, penetration-testing automation, or security operations.
• Experience with Security of AI, including LLM red teaming, adversarial machine learning, prompt injection, and agentic AI security.
• Familiarity with cybersecurity tools and environments such as CTFs, sandboxed exploitation environments, static/dynamic code analysis, and security testing frameworks.
• Experience developing cybersecurity benchmarks or evaluating frontier models on complex security-related tasks.

Responsibilities

• Conduct hands-on research in frontier AI models, reasoning, agents, and multimodal systems.
• Design, implement, and iterate on AI benchmarks, evaluation frameworks, and experimental pipelines.
• Execute short, high-impact research cycles, moving from hypotheses to experiments, prototypes, and validated findings.
• Identify model limitations, evaluation gaps, and emerging research opportunities.
• Work directly with customers and technical stakeholders to translate complex challenges into actionable research.
• Collaborate with engineering and product teams to turn research findings into practical solutions.

What This Job Offers

• Job Type: Full-time
• Career Level: Principal