Research Engineer - Agency and Reasoning

Highlights

• Core contributor to Agency and Reasoning team building next-gen language models.
• Perform novel research in RL, post-training and human preference learning.
• Apply research ideas at scale to advance ambitious next-generation models.

What they offer

• Comprehensive medical, dental, vision, and FSA plans
• 401(k) plan
• Unlimited PTO and company holidays
• In-office snacks and meals provided
• Relocation and immigration support on a case-by-case basis

Ideal candidate

Curious researcher who loves understanding intelligence and thrives in fast-paced collaboration, eager to take bold ideas from conception to large-scale experiment with grounded, methodical rigor.

Requirements

• Strong research taste and intuition with ability to take research from conception to execution to write-up
• Strong implementation and prototyping skillset, highly proficient with PyTorch and Python
• Experience with reinforcement learning for language model reasoning or classical RL tasks
• Experience with supervised fine-tuning and preference learning methods such as DPO and simPO
• Experience with context-length extension methods
• Ability to understand model behaviors and correct them through iterative fine-tuning and data engineering
• Postgraduate degree in Computer Science, EE/EECS, Mathematics, Physics or related scientific field
• Published machine learning research in well-respected venues
• Excellent communication and collaboration skills in a high-paced research setting