Hackathon Portal
AI Tinkerers - San Francisco
Final round winners have been announced. View Results
Team

YOO

Project Concept

Your Omniscient Other

Entry

Status: Submitted

Last saved: February 21 at 5:20 PM PST

Team Roster

You must be registered for the event to view the team message board.

Fadi Al Zuabi Team Lead RSVP Approved

Firmware/ AI Engineer at Solidigm
Fadi led the project strategy, architecture design, and implementation. Built the Atomic Router hybrid routing system in main.py using the Cactus Compute Python SDK for on-device FunctionGemma inference and the Google GenAI SDK (Gemini 2.5 Flash) as cloud fallback. Designed the regex-first multi-intent decomposition strategy, implemented manual argument extraction for all 7 tool types, and tuned the system from 30% baseline to 97.4% final score. Handled local environment setup (Cactus build, model download, API key configuration), benchmark iteration, and leaderboard submission.
Senior Firmware Engineer & AI Champion at Solidigm (SK Hynix). Syrian-American engineer who fled the Syrian Revolution in 2014, restarted education from scratch in the US, and made it to Silicon Valley through relentless learning. Journey: Damascus University (interrupted by war) โ†’ UIUC Electrical Engineering (3.70 GPA) โ†’ GE Aviation (aircraft health monitoring, first 4G-LTE in aviation) โ†’ Intel/Solidigm (Gen5 PCIe SSDs). Now bridging firmware and AI: created a 5-hour GitHub Copilot workshop and trained 84+ engineers across 7 workshops. Go-to person for AI initiatives company-wide. Building AI-powered debugging systems and designing firmware agents for automated bug solving. Core philosophy: "The most valuable skill is not what you know, but how quick
Looking to connect with: - AI/ML engineers working on developer tools and coding assistants - Founders building AI infrastructure or developer productivity tools - Engineers bridging hardware/firmware with AI (edge AI, intelligent systems) - People exploring AI agents for enterprise automation Want to learn more about: - Production-grade AI agent architectures - MLOps best practices at scale - AI chip design and specialized hardware for ML - Building AI-first companies from firmware/systems back
Building an Intelligent Firmware Debug Agent. evaluation with experimental Graph Neural Networks for dependency analysis. Also working on co-flow - a personal knowledge management system with GCP Firestore and Vertex AI embeddings. Building Pairlet.io for technical interviews. ๐Ÿฆž