Torin Nelson

About Me

Torin Nelson

Hi, I’m Torin. I’m a computer science graduate student specializing in machine learning and intelligent systems. I build high-performance desktop utilities, software tools, libraries, and ML models. My current focus is on video processing and optimization pipeline projects. When I’m not programming, you can usually find me training Brazilian Jiu Jitsu or gaming.

Professional Projects

HDR to SDR

Visit Site →

Desktop GUI application with over 2,500 downloads for converting HDR video to SDR using FFmpeg. Features a live side-by-side frame preview, multiple tonemappers (Reinhard, Mobius, Hable), and static or dynamic conversion modes. The Pro tier adds GPU-accelerated tonemapping via libplacebo (Vulkan), hardware encoding (NVENC / AMF / QSV), batch queue conversion, and a node-locked licensing system backed by hardware fingerprinting and HMAC-signed tokens.

AI Code Bot

GitHub →

Open-source AI coding assistant. Contributed as a software engineer by integrating Ollama as a model provider, enabling offline coding assistance with any locally hosted LLM (Llama 3, Mistral, etc.). Abstracted the model interface for dynamic configuration and expanded the test suite to validate Ollama API responses.

Sankaku Analytics Closed Source

ML-powered retail analytics platform for CPG companies. Ingests point-of-sale data from Nielsen, SPINS, IRI, and Whole Foods, then clusters SKU portfolios via K-Means, visualizes commercial DNA through radar and PCA charts, and surfaces prescriptive trade-spend and distribution recommendations through a rules-based strategy engine.

NASA L'SPACE PDR

Download PDF →

250-page Preliminary Design Review delivered to NASA as part of the L'SPACE Mission Concept Academy. Covers mission architecture, CDH subsystem design, trade studies, and a revised scope under a simulated 22% budget cut. Co-led as Deputy Project Manager and CDH Systems Lead.

Resume

Download PDF →

Skills

Python, Pytorch, REST, Git, Scikit-Learn, Machine Learning, Statistics, Hyperparameter Tuning, Data Cleaning, NLP, Quantum Algorithms, Quantitative Analysis, Application Development, AI-Assisted Programming

Education

University of Colorado, Boulder Expected Mar 2027
MSCS in Computer Science (AI Specialization) — 4.0 GPA
University of California, Irvine Jun 2024
B.S. in Computer Science (AI Specialization) — 3.7 GPA

Projects

HDR-to-SDR Color Mapping Utility — Python Jan 2024 – Present
  • Engineered a production-ready desktop app (2,500+ downloads) using Python and FFmpeg for high quality mathematical tone-mapping.
  • Designed a thread-safe, asynchronous rendering pipeline with real-time progress tracking, while securing binaries via machine fingerprinting and Azure signing.
  • Streamlined development using agentic AI (Claude) and rigorous TDD (Test Driven Development); employed unittest.mock to maintain a floor of 90% test coverage.
  • Developed a GPU-based video processing architecture that enhanced encoding performance by 400% through optimized support for Intel, AMD, and NVIDIA hardware.
Quantitative Analysis Betting Market Bot — Python Nov 2025 – Jan 2026
  • Engineered a comprehensive automated 24/7 trading bot for the Polymarket prediction platform using a robust Python execution engine.
  • Implemented a “Smart Copy” system to analyze historical user performance, filter luck-based variance, and identify consistently profitable traders.
  • Developed a stable, multithreaded polling architecture and complex execution rules, including slippage calculation and consensus weighting, to maximize profit.
Electricity Access Mapping via Attention UNet — Python Jan 2024 – Mar 2024
  • Developed an Attention UNet model using satellite imagery to identify underserved settlements in Sub-Saharan Africa lacking electricity.
  • Achieved 75% accuracy and implemented explainable AI methods for result interpretation.
  • Received the Future Prospects and Recognition Award for adapting a medical imaging model to satellite data.

Experience

Sankaku Analytics Feb 2026 – May 2026
Founding Engineer and CTO — Remote
  • Developed the MVP for a high-performance data analytics platform, focusing on scalable backend architecture and efficient data processing.
  • Implemented and optimized K-Means clustering algorithms for automated data segmentation and pattern discovery.
  • Architected the core system from the ground up, making critical decisions on tech stack and data integrity to support rapid prototyping and iteration.
  • Translated complex business requirements into a technical roadmap, balancing feature velocity with system stability.
AI Code Bot Oct 2023 – Mar 2025
Software Engineer, Open Source — Remote
  • Integrated Ollama as a model provider, enabling the application to connect with any locally hosted LLM (e.g., Llama 3, Mistral) for offline coding assistance.
  • Abstracted the model interface to support dynamic model configuration, allowing users to seamlessly swap between any Ollama-supported model without changing the codebase.
  • Expanded the existing test suite, writing new unit tests to validate Ollama API responses and ensure stability for local inference features.
NASA L'SPACE Apr 2024 – Sept 2024
Deputy Project Manager and CDH Systems Lead — Remote
  • Co-led a 12-person team through a NASA mission concept, delivering a 240-page PDR and revising the mission scope to fit a simulated 22% budget cut.
  • Defined CDH subsystem requirements, establishing variable data transmission rates (1s Science / 30s Telemetry) to prioritize bandwidth for critical mission phases.
  • Conducted trade studies for avionics and mechanical components (IMU, Motors), selecting hardware based on thermal operating ranges (−193°C to 111°C) and power budgets.

Personal Projects

Open Source

OpenTurbo

GitHub →

Experimental CUDA prototype for 3-bit KV-cache compression in LLM inference. Implements a TurboQuant-style FWHT encoder with QJL residual sign correction, GQA-aware scoring, and a downstream bridge targeting llama.cpp integration.

ShrinkWrap

GitHub →

CLI tool that compresses AI agent instruction files (CLAUDE.md, .cursorrules, system prompts) into a token-optimized format. Keeps security rules and architecture constraints byte-identical via SHA-256 checksums while aggressively deduplicating volatile status and todo sections.

Quantitative Analysis Betting Bot

GitHub →

24/7 automated trading bot for the Polymarket prediction platform. Implements a Smart Copy system that analyzes historical trader performance and filters luck-based variance to identify consistently profitable whales. Built on a multithreaded polling architecture with slippage calculation and consensus weighting. Simulated trades only; real execution is not implemented. Project is deprecated.

Heart Disease Prediction

GitHub →

Binary classification project predicting heart disease presence from clinical features. Compares Logistic Regression and Random Forest on the Kaggle heart disease dataset, with full EDA, feature importance analysis, and ROC curve evaluation. Random Forest achieved 100% test accuracy on this corpus.

Closed Source

Discord YouTube Bot

Self-hosted Discord music bot with YouTube playback, queue management, and playlist support. Uses yt-dlp with browser cookie fallback for age-restricted content and backs off automatically when YouTube rate-limits a session.

Electricity Access Mapping

Attention UNet trained on IEEE GRSS 2021 satellite imagery to identify underserved settlements in Sub-Saharan Africa lacking electricity access. Achieved 75% accuracy with GradCAM-based explainability. Received the Future Prospects and Recognition Award for adapting a medical imaging architecture to satellite data.