Misuse Red Team - Research Engineer/Research Scientist

Onsite London, UK

gopytorch red team

greenhouse

Match & cover letter

Create a profile to see your match and get a cover letter for this role.

Create profile and match

Job description

Join a team focused on researching and developing safeguards against AI misuse in London. You'll work with leading experts to tackle advanced AI risks and contribute to impactful research.

Details

London, UK, work from office
£65,000 to £145,000 annual salary
Experience with large language models and research publications required
Skills in Go and PyTorch

The work

Design and evaluate methods to automatically attack and assess safeguards
Build benchmarks for monitoring misuse and jailbreak development
Investigate novel attacks and defenses for data poisoning in LLMs
Perform adversarial testing of AI system safeguards and produce reports