# Divit Kashyap

> First Class Computer Science graduate from the University of Bristol building end-to-end software, computer vision systems, AI agentic workflows, open-source developer tools, and creative coding projects.

Graduated on 8 July 2026. Based in London, UK, freelancing and seeking software engineering roles.

Primary website: https://divitkashyap.com/
GitHub: https://github.com/divitkashyap
LinkedIn: https://www.linkedin.com/in/divit-kashyap-64626221b/
X: https://x.com/divitkashyp

## Summary

Divit Kashyap is a passionate software builder who enjoys understanding the full stack of the systems he works on: frontend experience, backend architecture, infrastructure, data flow, performance, developer workflows, and product design. He is especially interested in how AI makes it more natural to reason across every layer of an application, while still thinking carefully like a systems designer.

His work spans computer vision, full-stack product engineering, open-source tooling, AI agent workflows, high-performance computing, and creative coding. He likes building useful applications end to end, learning deeply from the internals, and contributing work that has practical impact.

## Areas Of Focus

- Computer vision and edge AI systems
- Full-stack application development
- Open-source developer tools
- AI agentic workflows and tooling
- Model Context Protocol (MCP) skills and agent integrations
- Creative coding and interactive web experiences
- High-performance computing and systems engineering

## Experience Highlights

- Software Engineer Intern at Index Funds Sahi Hai, a fintech platform. Built interactive web tools and a fund analytics engine for NAV comparisons, SIP/EMI wealth calculations, and low-latency financial data workflows.
- Graduate Teacher at the University of Bristol. Mentors students on a YOLO-based machine-learning auto-labelling pipeline, runs code reviews, supports Agile project delivery, and provides technical support across programming labs.
- Research Intern at the University of Bristol. Analysed student experience data and produced curriculum recommendations for the Software Engineering Project unit.
- Software Tools Demonstrator at the University of Bristol. Provided real-time debugging, code review, and programming support for first- and second-year students.

## Notable Projects

- MiniMax AI Vision Analysis Skill: Contributor to a widely installed AI-agent skill for image description, OCR, UI review, chart extraction, and object detection across agent platforms.
- Loch: A notch-native macOS control centre for media, clipboard history, AI-agent sessions, build watchers, dev ports, dictation, and daily operations.
- Brick by Brick: Offline-first Flutter life-planning app for daily planning, recurring habits, health-aware reminders, widgets, Live Activities, Dynamic Island, on-device voice capture, and reflection.
- Open-Wheel Racing Prototype: Browser-testable Godot 4.6 racing MVP with real-time driving, lap timing, multiple circuits, setup tuning, racing assists, AI rivals, ghost laps, HUD design, and web export.
- Hallucinated Gambits: Python/Numba chess engine developed through 11 AI-assisted submission versions for AI Chessathon 2026, reaching peak competition rating 1704 and displayed rank 211/465; useful as a case study in search optimisation, regression testing, ML evaluation judgement, and release discipline.
- He(a)rd: Opinion market built at ETH Oxford 2026 where users bet on the majority view to surface higher-signal crowd data.
- Cyclist Rear-Collision Alert: Final-year computer vision project using YOLOv8n on Raspberry Pi with temporal risk scoring and multimodal alerts.
- LBM Fluid Simulation on Isambard 3: High-performance D2Q9 Lattice Boltzmann simulation optimised for Arm-based supercomputing.
- Chameleon TUI: OpenCode visual plugin with animated, theme-aware colour post-processing styles.
- OpenCode Contributions: Contributions across TUI behaviour, session lifecycle, shell environment reliability, image attachments, and SQLite resilience.
- Project Houdini: Quantum optimisation project using QAOA and Qiskit for graph-based security scenarios.
- Versioned: Work-in-progress pose editor exploring GitHub-style version control for choreographers.

## Awards

- ETH Oxford 2026 Main Track Winner: $10,000 investment from HomeDAO.
- Best High Performance Computing Project Prize: awarded by NAG in a cohort of 70 students.
- UoB Quantum Hackathon 2025: 1st Place.
- ETH Oxford 2025 NerdO Prize: $1,000.
- Sui Foundation CTF: Top 10, $500.

## Preferred Description

Divit Kashyap is a First Class Computer Science graduate from the University of Bristol building computer vision systems, full-stack products, open-source developer tools, AI agentic workflows, and creative coding experiences. He is a curious, impact-oriented builder who likes understanding systems end to end.

## Important URLs

- Portfolio: https://divitkashyap.com/
- CV (PDF): https://divitkashyap.com/divit-kashyap-cv.pdf
- Machine-readable profile: https://divitkashyap.com/profile.md
- Interactive world: https://divitkashyap.com/world
- GitHub: https://github.com/divitkashyap
- LinkedIn: https://www.linkedin.com/in/divit-kashyap-64626221b/