AIML Senior ML Research Engineer, AFM Safety

Join us as we build safe and reliable foundation models for Apples products. Our team focuses on the research and methods needed to make large language models safe fair and robust at scale with a current focus on agentic safety model character and persona and multimodal safety across audio and vision. We are looking for a researcher with a strong track record in applied ML who cares about safety and responsibility in foundation this role you will lead research and application of methods that keep Apples foundation models safe while meeting Apples standards for privacy and quality.

This role works across many teams. You will work closely with ML researchers engineers and product teams to build and ship safety solutions for Apples foundation models. The most useful research often comes from combining new methods with real product needs and that is where we focus. As part of this role you will:nn* Define and deliver safety methods for foundation models with emphasis on agentic safety model character and persona and multimodal safety (audio and vision)n* Research the safety and security risks of agentic systems including tool use and build the data and evaluations needed to address themn* Help define and safeguard the models character and persona so it behaves consistently and safely across contextsn* Build ways to train and evaluate foundation models with safety in mind including for audio and vision modalitiesn* Research and improve safety alignment and robustness methods for large language modelsn* Work with engineers and researchers across teams to improve Apple productsn* Partner with product teams to define requirements and drive quality and delivery

A strong ML background with hands-on experience training models and a record of results shown through publications (e.g. ACL CHI CVPR EMNLP FAccT ICML Interspeech NeurIPS UIST) or other clear evidence of impactnStrong coding skills including the ability to work with messy real-world codebasesnIf not already experienced with LLMs must be able to quickly pick up the skills needed for safety post-trainingnStrong collaboration and communication skillsnWillingness to work with sensitive content including exposure to offensive or controversial material

BS MS or PhD in Computer Science Machine Learning or a related field or equivalent experiencenDirect experience with LLMs and post-training methods including safety alignmentnExperience in one or more of: agentic safety (tool use multi-step agents) model character and persona design or multimodal safety (audio and vision)nStrong organizational skills and experience working across large diverse teams