Building code intelligence systems
I build tools that help developers understand codebases. Currently focused on graph-based context retrieval, cross-file call resolution, and LLM-powered code analysis.
Projects
Supermodel
Code intelligence platform providing graph-based context retrieval for AI coding assistants. Built call graphs, dependency graphs, and domain classification using tree-sitter parsing and Louvain community detection.
Ghostie
CLI tool for managing AI context and memory across terminal sessions. Features knowledge graph capabilities with hashtags and wikilinks for persistent context.
Age of Claude
Experimental project exploring AI agent interactions and emergent behaviors in simulated environments.
Experience
Software Engineer
Jan 2025 - PresentSupermodel
- Built import resolution system handling bare imports, dotted paths, and extension inference across TypeScript, Python, Java, and Go
- Designed cross-file call graph construction with tree-sitter parsing and Neo4j graph storage
- Implemented domain classification using LLM-based labeling and Louvain community detection
- Created MCP server for Claude integration providing graph-based context retrieval
Math Trainer (AI/ML)
2024Outlier AI
- Designed adversarial math problems to train and evaluate LLM reasoning capabilities
- Created problem sets across calculus, linear algebra, probability, and discrete mathematics
- Evaluated model responses for correctness and mathematical reasoning quality
Data Analyst
2024ACI Seeds
- Built Python automation for seed quality data processing, reducing 8-hour manual workflows to 30 minutes
- Implemented data validation and automated Excel report generation
Technical Skills
Languages
Technologies
AI/ML
Infrastructure
Education
BS Mathematics
Indiana University
Real Analysis, Abstract Algebra, Topology, Probability Theory
AS Computer Science
Georgia State University
Data Structures, Algorithms, Discrete Mathematics