AIML Researcher/Engineer, Foundation Model Post-Training

What you'll do

• Design and refine post-training strategies to enhance model capabilities in instruction following and tool use.
• Develop novel algorithms for preference optimization, model safety, and steering techniques.
• Create high-quality data generation methods and automated filtering processes to improve training datasets.
• Establish robust evaluation frameworks to measure model performance beyond static benchmarks.
• Collaborate with pre-training teams to guide architectural decisions and align user needs with model functionalities.

What we're looking for

• Demonstrated expertise in deep learning with a focus on LLMs, post-training, or reinforcement learning.
• Proficiency in Python and a major deep learning framework such as JAX or PyTorch.
• Master's or PhD degree in Computer Science, Machine Learning, or a related technical field (or equivalent practical experience).
• Experience training state-of-the-art large models at scale with familiarity in distributed training challenges (preferred).
• Experience improving model performance on complex reasoning tasks such as math, coding, and logic (preferred).
• Experience with various transformer architectures and their transformations (preferred).
• Strong communication skills and a passion for working cross-functionally across Research and Product teams (preferred).