Research Engineer, Post-Training (All Industry Levels)

Job summary

Responsibilities

Joining us as a Research Engineer on the Post-Training team, you'll be diving into the exciting world of fine-tuning AI models, optimizing their performance, and ensuring they meet the highest standards of quality and efficiency.

• Develop alignment algorithms and loss functions to improve data sample efficiency.
• Write data pipelines to process diverse web data into a format models can ingest.
• Identify quality signals to understand our model’s performance in the real world.
• Design sampling algorithms to improve serving efficiency of large generative models.

What they're looking for

• "All Industry Levels": have at least PhD (or equivalent)
• Write clear and clean production-facing and training code
• Experience working with GPUs (training, serving, debugging)
• Experience with data pipelines and data infrastructure
• Strong understanding of modern machine learning techniques (reinforcement learning, transformers, etc)

Tech stack

• Transformers
• Kubernetes
• Docker