Research Scientist, Post Training

About the Role

This is a research scientist role focused on post-training, sitting at the heart of a team building the data layer that teaches frontier foundation models how experts think and reason. You will drive the design and execution of model optimization work that directly shapes how the next generation of AI systems learns from human expertise.

What You'll Do

• Design and implement post-training pipelines including supervised fine-tuning, reinforcement learning from human feedback, and related model optimization techniques.

• Build and evaluate reinforcement learning algorithms applied to large language models and transformer-based architectures.

• Plan and run rigorous machine learning experiments, defining evaluation methodologies and interpreting results to guide research direction.

• Develop and scale distributed training systems to support production and research model workloads.

• Contribute to published research or internal technical reports that advance the team's understanding of post-training methods.

What We're Looking For

• 3 or more years of hands-on machine learning research experience, specifically in post-training, reinforcement learning, or related model optimization.

• Demonstrated experience implementing reinforcement learning algorithms or post-training techniques in research or production settings.

• A track record of published research or shipped ML systems showing expertise in model training and optimization.

• Experience working with large language models or transformer-based architectures.

• Strong proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow.

• Experience with distributed training or scaling machine learning systems.

• PhD in machine learning, computer science, or a related field, or equivalent research experience.

• Contributions to open-source machine learning projects or frameworks are a plus.

Compensation & Benefits

Base salary range: $150,000 to $250,000 USD annually. Visa sponsorship is available.

Location

On-site in San Francisco, CA, USA.