Research Engineer - Agency and Reasoning
Zyphra· R&D - Engineering
San FranciscoFull-timePosted 11mo ago
About the role
Research Engineer focusing on Agency and Reasoning, performing novel research in reinforcement learning, post-training, and human preference learning, and applying ideas at scale to next-generation language models.
Responsibilities
- Perform novel research in reinforcement learning, post-training, and human preference learning.
- Apply ideas at scale to Zyphra’s language models.
- Contribute as a core member of the Agency and Reasoning Team from conception to execution, experiment, and write-up.
Qualifications
- Postgraduate degree in Computer Science, EE/EECS, Mathematics, Physics
- Previously published machine learning research in well-respected venues
- Highly proficient with PyTorch and Python
- Experience with reinforcement learning in language model reasoning or classical RL tasks
- Experience with language-model-supervised fine-tuning and preference-learning methods (e.g., DPO, simPO)
- Experience with context-length extension methods
- Ability to understand model behaviors and iterate via fine-tuning
- Interest in data engineering and synthetic data generation
- Excellent communication and collaboration skills, effective on research and engineering implementation at scale
Skills
Required:Reinforcement LearningLanguage-model-supervised fine-tuning and preference-learning (DPO, simPO)Context-length extension methodsPythonPyTorchCommunication and collaboration
Nice to have:Data engineering and synthetic data generation
Benefits
- Comprehensive medical, dental, vision, and FSA plans
- Competitive compensation and 401(k) plan
- Relocation and immigration support on a case-by-case basis
- In-office snacks and meals provided
- Unlimited PTO and company holidays
- In-person team in San Francisco with a collaborative, high-energy environment
Last updated Aug 6, 2026. Interested? Apply on the company site.
More open roles at Zyphra
- Machine Learning Systems Administrator / DevOps Engineer: Training Clusters & Inference Cloud4d agoSan Francisco · R&D - Engineering
- Research Engineer -- Vision and Vision-Language Models4d agoSan Francisco · R&D - Engineering
- Principal Solutions Architect7mo agoSan Francisco · GTM
- Developer Relations Lead7mo agoSan Francisco · GTM
- GTM Engineer7mo agoSan Francisco · GTM