Open Source Work
Projects
Setting up my local sandbox environment and writing modules. As I build these systems, the GitHub repositories and design architecture outlines will appear right here.
BENCHMARKING
mini-transformer-gpu
A custom language model architecture built from scratch in raw PyTorch. Features custom multi-head causal attention loops, BPE tokenization, and validation on consumer GPUs.
PRODUCTION
stream-elt-lakehouse
High-concurrency streaming pipeline ingesting millions of telemetry events per minute from Apache Kafka into Snowflake with real-time anomaly detection and strict schema enforcement.
RESEARCH
surprisal-llm-eval
Psycholinguistic predictability and surprisal modeling suite. Evaluates token probability matrices across fine-tuned LLMs against cognitive human reading benchmarks.