Description
Zyphra, an AI company in Palo Alto, CA, seeks a Research Scientist for its Agency and Reasoning Team. The role involves novel research in reinforcement learning, post-training, and human preference learning, applied to next-gen language models. Ideal candidates have strong research skills, implementation abilities, and experience with reinforcement learning, language model finetuning, and PyTorch/Python. A postgraduate degree in a scientific subject and published machine learning research are required. Zyphra values innovation, speed, and collaboration, offering comprehensive benefits and an energetic, in-person team environment.
