Position
Research Scientist (London)
Goodfire
- London, United Kingdom · On-site
- Artificial Intelligence, Deep Learning and
About
Goodfire is an AI interpretability research lab that builds interpretability agents and infrastructure to understand, monitor and align AI models. This research scientist develops new techniques for understanding and steering large AI models, working with the London team on mechanistic understanding of the algorithms neural networks have learned. Work spans foundational research on how models represent and process information, high-upside bets on new techniques for model understanding, and translating research into tools: prototyping methods to visualise and manipulate internal model structure and sharing results through publications, demos and open-source code.
The expected salary range is £150,000–£300,000 GBP.
Requirements
PhD or equivalent experience in machine learning, computer science or a quantitative science; deep familiarity with large models; fluency in Python and ML frameworks such as PyTorch; strong writing and communication skills. Preferred: experience leading research or contributing to open-source codebases, and familiarity with interpretability, alignment or safe model development.
Topics
Source: Goodfire