Machine Learning Researcher, Post-Training for Foundation Models

What you'll do

• Design and iterate on end-to-end post-training recipes using SFT, Reinforcement Learning, and reasoning regimes.
• Develop and implement novel algorithms for preference optimization, model steering, and safety.
• Research methods for high-quality human and synthetic data generation to improve instruction following.
• Implement automated data filtering and curriculum learning to enhance model reasoning capabilities.
• Design robust evaluation frameworks to measure model helpfulness, factuality, and real-world utility.
• Solve complex problems in reward modeling to prevent reward hacking and handle sparse rewards.
• Align models across a spectrum of tasks from creative content to precise action-taking workflows.

What we're looking for

• Demonstrated expertise in deep learning with a focus on LLMs, post-training, or reinforcement learning backed by a strong publication record or real-world experience.
• Proficiency in Python and at least one major deep learning framework such as JAX or PyTorch.
• PhD or equivalent practical experience in Computer Science, Machine Learning, or a related technical field.
• Proven track record in post-training algorithms, techniques, and best practices for large foundation models (preferred).
• Deep experience with human data labeling, synthetic data generation, and evaluation methodologies for foundation models (preferred).
• Experience improving model performance on reasoning tasks such as math, coding, or logic (preferred).
• Experience training state-of-the-art large models at scale and familiarity with distributed training challenges (preferred).
• Strong communication skills and a passion for collaboration across teams (preferred).