Experience
Been mostly having fun at the intersection of data, compute, and systems!
AWS Annapurna Labs - Neuron Compiler
Machine Learning Compilers Intern
May 2026 - August 2026
- Built an MLIR simulator in C++ to validate compiler-emitted IR across ~35 lowering passes
- Implemented 8 MLIR dialects with dynamic shapes, bufferization, and accelerator-faithful arithmetic
- Integrated the simulator as an MLIR pass for end-to-end testing and bisection, exposing GELU derivative drift
- Extending the simulator with vectorized linalg.generic execution and packed datatype support
USAA
Data Analyst Intern
May 2025 - August 2025
- Accelerated data processing 7× with Polars and concurrent roll-rate matrix computation
- Reduced loan chargeoff forecast percent error from 53% to 14% with ARMA modeling on log residuals
Morgridge Institute for Research
Research Intern
February 2024 - October 2024
- Published in BMC Bioinformatics
- Combined biomedical literature-based discovery with LLM hypothesis evaluation (feel free to play with it here)
- Fine-tuned LLM for biomedical text analysis with synthetic data (9,000+ downloads on HuggingFace!)
- Improved accuracy of RAG relevance filter from 70% to 90% with NEFTune and rsLoRA
- Sped up inference pipeline 15× via packed batching + vLLM on university HTC cluster