Goodfire is hiring a Research Scientist to develop new techniques for understanding and steering large AI models. You will work closely with a small, mission-driven team to conduct novel research, build practical tools, and push the field forward.
The London-based team focuses on mechanistic understanding of neural networks. You will contribute to foundational research, prototype visualization techniques, and collaborate with engineering to productionize research outcomes.
#J-18808-LjbffrInterpretability Scientist — Shape Safer AI Systems employer: Goodfire
Goodfire is an exceptional employer, offering a unique opportunity to work at the forefront of AI interpretability in London. With a strong focus on team collaboration and personal ownership, employees are encouraged to innovate and contribute to groundbreaking research while enjoying competitive salaries and equity. The vibrant work culture fosters continuous improvement and provides ample growth opportunities, making it an ideal environment for those passionate about shaping the future of AI.
