Nicholas Tweedie NicholasHat

Hi, I'm Nicholas Tweedie 👋

I am a Software Engineering student at the University of California, Irvine interested in innovative applications of AI.

Category	Technologies
Languages	Python, TypeScript, JavaScript, Swift, C/C++, SQL, Java
AI & Machine Learning	Ollama, Hugging Face, Scikit-Learn, Core ML, MLX, AWS SageMaker, AWS Bedrock, Pydantic
Backend & Cloud Infrastructure	FastAPI, AWS (Lambda, API Gateway), Docker, WebRTC, RESTful APIs
Frontend & 3D Visualization	Next.js, React, Three.js, TailwindCSS
Systems & Development	Git

Speculative decoding across the Apple Neural Engine and GPU on a single chip, using public APIs only.

Stack: Swift, Python, Core ML, MLX/Metal.
Key Feature: Runs a draft model on the ANE and a target model on the GPU in parallel, achieving a 1.47× speedup over GPU-only decoding with the ANE draft fully hidden inside the GPU's verify window. Includes a custom measurement harness and handoff characterization protocol.

A local development environment and orchestration layer for open-source LLMs.

Stack: Python, FastAPI, Docker, Ollama / Hugging Face.
Key Feature: Provides an asynchronous API wrapper to deploy and run quantized open-source models locally with optimized inference and custom agent workflows.

A full-stack civic transparency platform and data pipeline.

Stack: Python, Next.js, Machine Learning (Scikit-Learn).
Key Feature: Utilizes an Isolation Forest machine learning architecture to analyze anomalies and trace patterns in congressional stock disclosures.

An AWS serverless platform for real-time sign language translation.

Stack: AWS Lambda, SageMaker, Bedrock, WebRTC.
Key Feature: Orchestrates real-time video streaming processing to translate American Sign Language (ASL) gestures instantly via serverless AI workflows.