Research Intern, Model Shaping (Winter 2027)

Job summary

Responsibilities

As a Research Intern in the Model Shaping team, you will work on one or more of the following areas:

• Advanced post-training methods across supervised learning, preference optimization, and reinforcement learning
• New techniques and systems for efficient training of neural networks (e.g., distributed training, algorithmic improvements, optimization methods)
• Robust and reliable evaluation of foundation model capabilities
• Escaping the Verifier: Learning to Reason via Demonstrations (ICML 2026)
• Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking (ICML 2026)

What they're looking for

• Currently pursuing a Bachelor's, Master's, or Ph.D. degree in Computer Science, Electrical Engineering, or a related field
• Strong knowledge of Machine Learning and Deep Learning fundamentals
• Experience with deep learning frameworks (PyTorch, JAX, etc.)
• Familiarity with the Transformer architecture and recent developments in foundation models
• Prior research experience with training foundation models or efficient machine learning

Tech stack

• PyTorch
• JAX