Member of Technical Staff, Post Training

What you'll do

• Develop data collection and acquisition methods for large language models.
• Build evaluations to measure model capabilities in coding, reasoning, and math.
• Apply advanced reward modeling and reinforcement learning techniques to improve post-training recipes.
• Design hypotheses and experiment plans to rapidly iterate on model performance.
• Perform synthetic data generation, curation, and cleaning for training pipelines.
• Drive the development of models that are safety-aligned and anchored to human values.
• Take end-to-end ownership of projects within a fast-paced research environment.

What we're looking for

• Bachelor's Degree in Computer Science, Machine Learning, Mathematics, or related technical discipline and 4+ years of engineering experience.
• Experience with reward modeling, RL, or other post-training techniques.
• Proficiency in coding using languages such as C, C++, C#, Java, JavaScript, or Python.
• Demonstrated experience in large-scale AI (preferred).
• Passionate about conversational AI and its deployment (preferred).
• Strong written and verbal communication skills to work with cross-functional teams (preferred).
• Ability to collaborate in a positive, inclusive environment and stay updated on AI trends (preferred).