Research Scientist - Ai Safety - Llms

Research Scientist - AI Safety - LLMs We are currently partnered with a hugely exciting AI Safety Startup who are looking to expand their Research Science team. The business, led by ex-Harvard/Stanford/Berkeley Researchers, are building advanced Safety tooling for large AI models, specifically Large Language Models (LLMs). As a Research Scientist, your role will see you apply the latest research in AI Safety to Large Language Models, with the aim of developing a suite of cutting-edge tools for Foundation Model providers (product is already used by OpenAI, Anthropic, AI21 and more) as well as end-users. This position will involve a mix of theoretical and applied research, with a particular focus on Synthetic Data Generation, Active Learning and Adversarial Attacks. Key skills required: -> PhD or MS in a relevant field - ML, CS, Applied Mathematics etc. -> AI Safety Research experience, ideally in a practical/commercial setting -> Experience in one of; Synthetic Data Generation, Active Learning and/or Adversarial Attacks -> Strong Python and general coding skills Please apply ASAP for more info!