Staff Applied Research and ML , Responsible AI and Safety

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

Applied research on the safety of LLMs and diffusion models in Apple's generative AI products. The work covers red teaming, safeguards for deploying LLMs in Apple products, and tools, metrics and datasets for evaluating model safety across the deployment lifecycle.

• AI misuse and jailbreaks

What you'd do

• Research and advance red teaming methods for LLMs and diffusion models.
• Research and develop mitigations and safeguards for safe deployment of LLMs in Apple products.
• Develop tools, metrics and datasets for assessing LLM safety over the model deployment lifecycle.
• Build methods and tools to interpret and explain failures in language models.

What it asks for

• PhD or equivalent experience in computer science or a related technical field is helpful.
• Track record in ML research, production deployment, or both.
• Deep understanding of LLMs.
• Working knowledge of deep learning frameworks such as TensorFlow or PyTorch.
• Ability to formulate a research problem, design experiments, implement and communicate solutions.
• Publication record in relevant conferences such as NeurIPS, ICML, ICLR or EMNLP (preferred).
• Prior work on responsible AI and AI safety (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 Applenorth_east before you apply. If we got something wrong, report this listing.