Research Scientist - Agency and Reasoning

Job Overview Zyphra is an artificial intelligence company based in San Francisco, California. As a Research Scientist, you will be a core contributor to Zyphra’s Agency and Reasoning Team, performing novel research in reinforcement learning, post-training, and human preference learning, and applying your ideas at scale to the next generation of language models. Responsibilities Apply a research-driven approach to develop and prototype advanced reinforcement learning methods, post-training techniques, and preference-learning systems for language models. Work from concept through to execution, including experimentation, data engineering, synthetic data generation, and iterative fine-tuning. Collaborate with a high-paced research team to rapidly prototype and scale solutions. Qualifications Strong research taste and intuitive understanding of AI and machine learning. Experience with reinforcement learning, including language-model reasoning or classical RL tasks. Experience with language-model supervised fine-tuning and preference-learning methods such as DPO and simPO. Familiarity with context-length extension methods. Ability to understand model behaviors and refine them through iterative fine-tuning. Published research in well-respected machine-learning venues. Postgraduate degree in Computer Science, EE/EECS, Mathematics, Physics, or related field. High proficiency in PyTorch and Python. Excellent communication and collaboration skills, able to work on both research and engineering implementation at scale. Curiosity and joy in understanding intelligence, with a desire to learn new fields rapidly. Why Work at Zyphra We strongly value new and crazy ideas and are very willing to bet big on them. We move as quickly as we can, aiming to minimize the bar to impact. We all enjoy what we do and love discussing AI. Benefits and Perks Comprehensive medical, dental, vision, and FSA plans. Competitive compensation and 401(k). Relocation and immigration support on a case-by-case basis. On-site meals prepared by a dedicated culinary team; Thursday happy hours. In-person collaborative, high- energy environment in San Francisco, California. #J-18808-Ljbffr SupportFinity™