Research Scientist - Mechanistic Interpretability

Our goal is to establish a foundation model of the brain by leveraging recent advances in neurotechnology and machine learning.

Job Requirements

• Design scalable analysis pipelines for mechanistic interpretability analyses of large neural networks, ensuring efficient data processing and accurate results.
• Develop automated feature visualization techniques to understand neural representations, utilizing advanced algorithms and computational methods.
• Build tools for circuit discovery and geometric analysis of population activity, providing valuable insights into brain function and behavior.
• Create reproducible analysis workflows that can handle large-scale neural data, applying principles of software engineering and data science.
• Collaborate with researchers to design and implement novel interpretability methods, fostering a culture of innovation and collaboration.
• Maintain distributed computing infrastructure for running interpretability analyses, ensuring scalability and reliability.
• Document findings through technical reports and visualization tools, facilitating knowledge sharing and dissemination.