Description
Google is hiring a Research Engineer for its Responsibility team to design and scale evaluation frameworks for harmful manipulation in frontier language models, develop detection and mitigation techniques, and build infrastructure to track model safety performance across releases. The role partners with research scientists, safety policy teams, and product stakeholders, and requires a relevant bachelor's degree or equivalent practical experience, three years of Python experience, and three years of experience with ML frameworks such as JAX, PyTorch, or TensorFlow.
