Tyson Lee Woodruff

212 Hartford Dr, Lodi, CA 95240

Email: tysonlee@humanalyzer.comPhone: 510-760-0471

Willing to relocate immediately to Phoenix/Goodyear, AZ for AI/GPU data center technician or infrastructure support roles.

Professional Summary

Dedicated IT Technician, Full-Stack AI Developer, and OSHA 10 + NFPA 70E certified professional with hands-on experience in hardware troubleshooting, PC/server imaging (MECM/SCCM), networking, Active Directory, and ticketing systems (ServiceNow/SharePoint). Solo-built production AI platforms including Humanalyzer.ai (cloud-scale OpenAI orchestration with vector embeddings/semantic search) and Kyrella (local GPU-accelerated LLM inference using PyTorch, Llama 3.1 8B quantization). Vibecoded (AI-accelerated development via Cursor/Claude/Groq) complex applications while overcoming personal challenges. Eager to apply AI tool expertise, GPU resource management, and safety training to hands-on data center operations in Phoenix's AI boom.

Education & Training

Self-Taught Developer

5+ years hands-on IT experience, continuous learning through certifications and building production systems

Certifications

Technical Skills

AI/ML & GPU-Related

OpenAI GPT-4/5 API, Prompt Engineering, Token Optimization, Vector Embeddings (pgvector), Semantic Search, Local LLM Inference (Llama 3.1 8B, Qwen2.5), PyTorch, BitsAndBytes 4-bit Quantization, NVIDIA GPU Management, Vibecoding (Cursor/Claude/Groq)

Hardware & Data Center

Server/PC Imaging (MECM/SCCM), Hardware Replacement/Upgrades, Troubleshooting, Networking (TCP/IP, VLANs, Routers/Switches), Cabling, VMware Virtualization, Linux/Windows/macOS Admin

Development & Operations

React/TypeScript, FastAPI/Python, PostgreSQL/Supabase, RESTful APIs, Vercel/Railway Deployment, Stripe, Git/GitHub, Active Directory/M365, ServiceNow/SharePoint

Security & Other

JWT/Row-Level Security, Endpoint Protection, Data Compliance, Raspberry Pi/Arduino, User Training/Documentation

Professional Experience

T-Mobile — Mobile Expert (Walnut Creek, CA)

June 2025 – Present (8 months)
  • Provide expert technical support for mobile devices and network issues
  • Educate customers on T-Mobile products, services, and features
  • Resolve complex technical problems with Android and iOS devices
  • Balance full-time work with building AI projects during off-hours

Geeker — Remote IT Technician

April 2023 – February 2025
  • Provided remote/on-site technical support, troubleshooting hardware, software, and network issues
  • Assisted with PC imaging/building using MECM (SCCM) task sequences; deployed software packages
  • Managed Active Directory (user accounts, password resets, permissions, domain joins, group policies)
  • Integrated AI tools (ChatGPT, Claude, Groq, Cursor) to automate troubleshooting workflows

Phillips 66 — IT Technician

February 2023 – June 2023
  • Led installation, maintenance, and optimization of computer systems and surveillance/IP cameras
  • Delivered cross-department IT support; executed system upgrades and security enhancements
  • Managed Active Directory and escalated tickets in ServiceNow/SharePoint

Cost Plus World Market — Help Desk Technician

May 2023 – July 2023
  • Administered Microsoft 365; diagnosed and resolved hardware/software issues remotely
  • Supported PC imaging (MECM/SCCM) and conducted M365 training sessions

Silverado Contractors / CyberCSI — Desktop Technician / L2 Engineer

March 2022 – March 2023
  • Provided comprehensive Windows/macOS support; resolved complex hardware/software/networking issues
  • Handled escalated tickets; managed Active Directory and GPO updates
  • Coordinated hardware refresh projects and vendor collaborations

Key Projects (Solo-Developed)

Humanalyzer.ai — AI Behavioral Intelligence & Coaching SaaS Platform (2025 – Present)

  • Developed full production AI platform (90,118+ files, 857 MB) for emotional awareness and relationship coaching
  • Stack: React/TypeScript, FastAPI/Python, PostgreSQL/Supabase, OpenAI GPT-4/5, Vector Embeddings, Vercel/Railway/Stripe
  • Metrics: 434+ AI analyses, 393+ sessions; demonstrates AI orchestration and deployment at scale

Kyrella — Local GPU AI Assistant with Two-Model RAG Architecture (2025 – Present)

GitHub: github.com/ForgeBorn87/Kyrella-public

  • Two-model system: Llama 3.1 8B (main brain, ~5GB) + Qwen2.5 3B (router/RAG, ~2GB) running simultaneously on one GPU
  • "Poor man's RAG": Token-based chunking + smart summarization for retrieval without vector DB overhead
  • Three-layer memory (short-term summaries, long-term facts, auto-learning), dynamic token allocation (512–8,192), tool integration

Use your browser's print function to save as PDF