Job Description

The theory/analysis team at Enigma is seeking Research Engineers & Research Scientists specializing in mechanistic interpretability to develop and deploy scalable methods & pipelines for interpreting mechanisms, representations, and circuits within our brain foundation models. The role presents a unique opportunity to fuse mechanistic interpretability with neuroscience, uncovering principles of natural intelligence.

The Enigma Project ( is a Stanford-based non-profit research organization, launched in August 2024 with $30M in funding. Our core mission is to leverage deep learning to crack the neural code. We own the full neuroAI pipeline: from neurotechnology development, to neural data collection, to modeling, theory, & analysis.

Role & Responsibilities :

• Lead development & implementation of automated methods for interpreting large-scale neural networks and biological data
• Design algorithms for discovering computational principles and circuits in neural systems
• Advance techniques for feature visualization, geometric analysis, and manifold learning in high-dimensional neural data
• Develop causal intervention methods to map information flow in neural networks
• Create tools for automated hypothesis generation and testing in neural systems
• Collaborate with neuroscientists to validate interpretability findings in biological systems
• Guide technical strategy for scaling interpretability methods to massive datasets

Key Qualifications :

• For Engineer: B.S. in Computer Science, Mathematics, Neuroscience, or related field plus 2+ years experience
• For Scientist: Ph.D. in Computer Science, Mathematics, Neuroscience, or related field -- or equivalent experience
• Strong record of research or engineering in machine learning, particularly in areas related to model interpretability
• Deep understanding of mechanistic interpretability literature and methods
• Expertise in analyzing and interpreting deep neural networks
• Strong programming skills with experience in modern ML frameworks
• Excellent written and verbal communication skills

Preferred Qualifications :

• Experience with automated scientific discovery systems or agentic AI
• Experience developing novel interpretability methods
• Background in theoretical neuroscience or computational neuroscience
• Knowledge of differential geometry and its applications to neural representations
• Familiarity with large-scale machine learning systems
• Track record of open-source contributions to interpretability tools
• Experience with large language models or multimodal architectures
• History of successful research collaborations across disciplines
• Demonstrated ability to lead research projects and mentor others

Research Areas of Interest :

• Novel methods for mechanistic interpretability at scale
• Geometric approaches to understanding neural representations
• Development of AI scientists for automated hypothesis generation and testing
• Techniques for discovering and validating computational circuits
• Comparative analyses between artificial and biological neural networks
• Causal intervention methods for understanding network computation
• Mathematical frameworks for neural information processing

What We Offer :

• An environment in which to pursue fundamental research questions in AI and neuroscience interpretability
• Access to unique datasets spanning artificial and biological neural networks
• State-of-the-art computing infrastructure
• Competitive salary and benefits package
• Collaborative environment at the intersection of multiple disciplines
• Location at Stanford University with access to its world-class research community

Application : Please send your CV and a one-page statement of interest to: recruiting@enigmaproject.ai

Job Tags

Similar Jobs