Understanding
the nature of intelligence
Goodfire is an AI interpretability research company focused on understanding and intentionally designing the next frontier of safe and powerful AI systems.
We're building Ember - the universal platform for neural programming
Ember decodes the neurons of an AI model to give direct, programmable access to its internal representations. By moving beyond black-box inputs and outputs, Ember unlocks entirely new ways to apply, train, and align AI models — allowing users to discover new knowledge hidden in their model, precisely shape its behaviors, and improve its performance.
Interpret
Uncover useful neural representations encoded in your model with an unsupervised approach that works across domains and architectures
Discover
Label neural representations with natural language descriptions to uncover knowledge used by the model
Design
Offline and inference-time neural program your model to control behavior and improve performance
Research
Careers
We're looking for agentic, mission-driven, and kind people to help us build the future of interpretability. If you thrive in fast-paced environments and believe that understanding AI systems is essential for our future, join us.
All roles are full-time, in person five days a week at our San Francisco, Telegraph Hill office.
Contact Us
Interested in Goodfire Ember? Contact us for a demo to see how we can help you understand and design your model.