ML Research Engineer - RL & Agentic Reasoning

Summary

Join Apple’s Generative AI team in Zurich as a Machine Learning Engineer specializing in foundation model post-training! Our team advances reinforcement learning (RL) for agentic tool use, planning and reasoning to enhance Apple’s foundation models. Our work directly shapes Apple Intelligence features such as Siri—impacting billions of users—while contributing to state-of-the-art research. You’ll collaborate with a dedicated group of researchers in Zurich and work closely with Apple’s core Foundation Model teams in Cupertino and NY.

Minimum Qualifications

MSc, PhD, or equivalent research/industry experience in Computer Science, Machine Learning, Electrical Engineering, or a related field. 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.

Preferred Qualifications

Publications in top ML/AI venues, or equivalent contributions through open-source or impactful industry work. 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.

Description

In our team, you will: - 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!