Description
Radical Numerics is hiring a Member of Technical Staff, Mechanistic Interpretability to research how multimodal genome language models represent, process, and reason about information. The role focuses on developing experiments, tools, theories, and interpretability workflows to uncover internal model mechanisms, connect them to capabilities and failures, and improve model evaluation, reliability, safety, and scientific discovery. Candidates should have a strong background in machine learning research, deep learning architectures, Python and PyTorch, experimental design, and scientific communication.
