Research Engineer: Interpretability, Theory, & Analysis

The theory/analysis team at Enigma is seeking Research Engineers 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 (https://enigmaproject.ai) 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:

• Design and implement scalable pipelines for automated interpretability analyses of brain foundation models
• Develop infrastructure for running massive-scale in silico experiments on digital twins
• Build tools for automated circuit discovery and geometric/topological analysis of neural manifolds
• Create efficient, reproducible analysis workflows for processing high-dimensional neural data
• Engineer systems for automated hypothesis generation and testing
• Implement and scale feature visualization and manifold learning techniques
• Maintain distributed computing infrastructure for parallel interpretability analyses
• Develop interactive visualization tools for exploring neural representations

Key Qualifications:

• Master's degree in Computer Science or related field with 2+ years of relevant industry experience, OR Bachelor's degree with 4+ years of relevant industry experience
• Strong understanding of mechanistic interpretability techniques and research literature
• Expertise in implementing and scaling ML analysis pipelines
• Experience with high-performance computing and distributed systems
• Proficiency in Python and deep learning frameworks (i.e., PyTorch)
• Experience with distributed computing and high-performance computing clusters
• Strong software engineering practices including version control, testing, and documentation
• Familiarity with visualization tools and techniques for high-dimensional data

Preferred Qualifications:

• Experience with feature visualization techniques (e.g., activation maximization, attribution methods)
• Knowledge of geometric methods for analyzing neural population activity
• Familiarity with circuit discovery techniques in neural networks
• Experience with large-scale data processing frameworks
• Background in neuroscience or computational neuroscience
• Contributions to open-source ML or interpretability tools
• Experience with ML experiment tracking platforms (W&B, MLflow)

What We Offer:

• Opportunity to work on fundamental questions in AI interpretability and neuroscience
• Collaborative environment bridging academic research and engineering excellence
• Access to state-of-the-art computing resources and unique neural datasets
• Competitive salary and benefits
• Career development and mentoring
• Location at Stanford University with access to its vibrant research community

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