Local AI Toolkit for Apple Silicon
Apple's on-device AI frameworks each need their own glue code, and most everyday tasks do not justify a cloud round-trip. This brings vision, audio, speech, and language models together into one Unix-composable, local-first CLI toolkit.
View Details →gRPC Embedding & LLM Serving Pipeline
Production gRPC infrastructure for text embeddings (rpcembed) and vLLM-based LLM serving, forming the AI inference stack that powers semantic search and RAG for agents at Accretional.
View Details →Statue Static Site Generator
Accretional's open source static site generator, built on SvelteKit and Markdown. This portfolio is built with it.
View Details →Distributed Platform Backend
The storage, search, and hosting backend that runs Accretional's cloud platform, a protobuf data store with semantic search, and the pieces that put a container or a site online.
View Details →OpenVINO Go Bindings
No production-grade Go bindings existed for Intel's OpenVINO Runtime, which outperforms ONNX on Intel CPUs, so I wrote them from scratch: idiomatic Go/CGO with async inference and variable state, benchmarking 40% faster than ONNX Runtime.
View Details →Formal Grammars as Protocol Buffers
Supporting a new format normally means hand-writing a parser and renderer and keeping them in sync forever. This compiler generates the whole type system from the grammar itself, so parsing and rendering fall out for free across 10+ formats, up to the ARM64 instruction set.
View Details →Browser Automation over gRPC
Selector-based automation shatters the moment a page changes. This exposes the Chrome DevTools Protocol as a gRPC service and adds a vision-guided agent that acts on what a page actually looks like, so automation survives pages never built to be scripted.
View Details →REST APIs as Typed gRPC Services
Integrating a third-party REST API usually means a bespoke client that rots as the API changes. This generates a typed gRPC service straight from the OpenAPI spec and regenerates from upstream, proven on the full OpenAI and Cloudflare APIs.
View Details →Founding Engineer - Infrastructure & Platform
Founding engineer owning AI infrastructure and platform systems across the stack, the ML inference layer (gRPC embedding and vLLM serving), the storage and semantic-search data layer, one-click publishing and hosting, and the platform's security and identity layer, alongside open-source work on an inference runtime, a grammar-to-protobuf compiler, and a REST-to-gRPC generator.
View Details →CT Denoising and Explainability using OT-CycleGAN
Adapted OT-CycleGAN for denoising ultra-low-dose CT scans with explainability features using Grad-CAM and attention visualizations
View Details →Prompt and Workflow Tooling for an AI-Native IDE
The file-backed prompt and workflow system, and the deployment and auth integration, inside a container-based remote IDE built for working with coding agents.
View Details →AI Engineering Intern
Built core features for Brilliant, an AI coding assistant. Worked on RAG pipelines, LLM fine-tuning, and the extension's prompt and deployment systems.
View Details →Semantifly: Local RAG for Coding Agents
A command-line tool that gives AI coding agents local retrieval-augmented generation over your own code and data.
View Details →Academic Lecture Video Summariser
LLM and RAG-based system for summarizing long-form academic videos
View Details →Whispers of the Heart - AI Therapy Assistant
Python-based conversational AI system for journaling and therapeutic assistance
View Details →Senior Machine Learning Scientist
Led ML initiatives for real-time loan processing. Built A/B testing frameworks and optimized system performance at scale.
View Details →Master of Science
Focused on machine learning and AI, particularly medical imaging applications. Research includes CT scan denoising and AI explainability. GPA: 3.9
View Details →GeneWeaver
A parametric hardware generator for DNA sequence alignment implemented in Scala
View Details →Machine Learning Scientist
Optimized ML inference pipelines from 200ms to 80ms through quantization and caching. Built LSTM forecasting models and production systems handling 1M+ requests/month at 99.9% uptime.
View Details →Machine Learning Research Intern
Built LSTM-based sentiment analysis pipelines for social media data. Applied model pruning and quantization techniques for efficient deployment.
View Details →Bachelor of Technology
Focused on machine learning and AI, with research in medical image analysis including published work on prostate cancer grading. GPA: 9.4 (Honors)
View Details →