Principal AI Research Scientist (Israel / UK)

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

This is a hands-on research role on frontier AI models, benchmarking and evaluation, with a cybersecurity focus, at a company that provides safety and security solutions for online experiences and GenAI products. The posting says the work includes building evaluation frameworks and turning research into customer-facing solutions for safety and security teams.

• AI misuse and jailbreaks

What you'd do

• Run hands-on research on frontier models, reasoning, agents and multimodal systems.
• Design, build and iterate on AI benchmarks, evaluation frameworks and experiment pipelines.
• Move through short research cycles from hypotheses to prototypes, experiments and validated findings.
• Identify model limitations, evaluation gaps and emerging research opportunities.
• Meet with customers and technical contacts to reframe their problems as research questions.
• Partner with engineering and product teams to turn findings into practical solutions.

What it asks for

• Advanced degree (PhD or MSc) in computer science, AI, machine learning or a related field, with strong research experience.
• Publication record at leading AI/ML venues such as NeurIPS, ICML, ICLR or ACL.
• Advanced Python and PyTorch, with experience building and evaluating complex AI systems.
• Working knowledge of how large language models and foundation models are tested and scored.
• 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 ML or prompt injection (preferred).
• Familiarity with CTFs, sandboxed exploitation environments and code analysis tools (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.