Role overview
Develop and scale RL methods to improve reasoning, instruction following, multi-turn dialogue, and reduce hallucinations in large language models.
Design and train agents with tool use, planning, and API integration to reliably accomplish tasks.
Build and refine reward models, evaluators, datasets, and simulation environments (e.g., for RLHF, RLAIF, and RLVF).
Run large-scale experiments, analyze results, and translate findings into both research contributions and practical improvements for Apple Intelligence.
Collaborate within a Europe-based team of ~35 RL/ML experts, coordinating closely with Apple’s foundation model groups in the U.S.
We value researchers eager to explore the space between fundamental research and applied work-with opportunities to contribute to both scientific progress and real-world applications!
What we're looking for
Hands-on experience with tool use, planning, retrieval, and agentic integrations for LLMs.
Experience with data curation, evaluation frameworks, and safety/guardrail methods.
Ability to design and implement experiments at scale, and to develop innovative approaches to challenging problems.
Strong background in reinforcement learning and deep learning, with hands-on experience training large-scale models, particularly LLMs.
Proficiency in Python and modern ML frameworks (e.g., PyTorch, JAX), with demonstrated experience in distributed training.
Ability to collaborate in interdisciplinary teams and clearly communicate complex concepts to both technical and non-technical partners.
At Apple, we’re not all the same. And that’s our greatest strength. We draw on the differences in who we are, what we’ve experienced, and how we think. Because to create products that serve everyone, we believe in including everyone. Therefore, we are committed to treating all applicants fairly and equally. We will work with applicants to make any reasonable accommodations.