Principal AI Research Cybersecurity Scientist (Bay Area)

Written by the T&S Network from Alice's posting.

Hands-on research on frontier AI models, benchmarking and evaluation, sitting in a team that builds security and safety solutions for online experiences. The role pairs research with customer problems, turning them into measurable experiments and findings for engineering and product teams.

• AI misuse and jailbreaks

What you'd do

• Run hands-on research into frontier models, reasoning, agents, and multimodal systems.
• Build and revise AI benchmarks, evaluation frameworks, and experiment pipelines.
• Run short research cycles from hypothesis to experiment, prototype, and validated finding.
• Spot where models fall short and where evaluation coverage is missing or new research is worth pursuing.
• Talk with customers and technical contacts directly, reframing their problems as research questions.
• Work with engineering and product teams to move research results into practical solutions.

What it asks for

• Strong publication record at top AI/ML venues such as NeurIPS, ICML, ICLR, or ACL.
• Advanced Python and PyTorch, with experience building and evaluating complex AI systems.
• Experience with AI for cybersecurity, such as autonomous security agents or vulnerability research (preferred).
• Experience with security of AI, such as LLM red teaming, adversarial machine learning, or prompt injection (preferred).

Terms in this role

Red teaming.

Testing a system, often an AI model, by deliberately trying to make it fail or misbehave, so problems are found and fixed first.

Our best summary of the posting, and it can be wrong. The employer's posting is what counts: read it in full on Alicenorth_east before you apply. If we got something wrong, report this listing.