Crafting digital excellence for AI/ML

TaSain Valdez Thomas

Software engineer who builds production software and translates ML research into working systems — a C++/SQLite worker-matching engine adopted by a plant, a conformal-prediction BMI estimator, and a phishing-campaign simulator.

90.4%
Conformal Coverage
2.81
MAE (BMI points)
11.56%
MAPE
7,208
Real Images
6,174
Labeled Images
90%
Prediction Interval
Download Resume PDF · 1 page

What I've built

Research-to-prototype systems at the intersection of AI and infrastructure.

PyTorch · Conformal · LLM-as-JudgeApr 2026 – Present github.com/T-Thomas1/BMI-Estimator-with-Reasoning ↗
Node.js · MySQL · JWT · SMTPJan 2025 – May 2025 github.com/WSU-4110/PhishingSimulator ↗

Phishing Campaign Simulator (Security Awareness)

Built a phishing-campaign simulator that sends templated emails over SMTP with a tracking pixel, logging open/click metrics in MySQL for security-awareness training.

  • JWT (jsonwebtoken) authentication with token-scoped separation of user vs admin views and least-privilege data access
  • Analytics pipeline built on a command design pattern, routing events to a formatting service
  • Vanilla HTML/CSS/JS front end on a Node.js backend
Flutter · Dart · PDF · GitFlowJan 2026 – May 2026

Client Project — PDF Editing & File Management (Flutter)

Capstone — Wayne State University (NDA: tech stack and role only). Team lead of a 4-person team building a Flutter collaboration app for a real client.

  • Personally built the PDF editor — floating toolbar (pen/pencil/eraser) layering annotations over a PDF and flattening to a single saved page, with an app-bar of undo/redo/delete/save and a text-insert command
  • Revised the in-app activity meter tracking user progress and time spent
  • Ran the team process — three weekly meetings, client communication, and a GitFlow branching/PR workflow
Proxmox · GPU Passthrough · HomelabMar 2026 – Present

Homelab — Privacy-First AI Inference

Self-hosted homelab for privacy-first AI serving — a Proxmox hypervisor with GPU passthrough running an AI agent inside a dedicated virtual machine.

  • Configured memory and resource allocation across nodes; assembled and connected the hardware end to end
  • Built for data privacy — serving models locally without third-party cloud dependencies
AI Orchestration · Stripe · TelegramMay 2020 – Present github.com/T-Thomas1/on-wheels_detailing-crm ↗

On-Wheels Detailing — Founder & AI Agent Orchestration

Founded and operate a detailing business with paying customers; wired up Stripe payment processing end to end.

  • Orchestrated a self-hosted AI agent to design and generate the business site via prompt-engineered role-play, with a no-customer-data-persisted privacy constraint
  • Built a Telegram agent layer delivering daily morning briefings and real-time lead alerts
  • Automated scheduled social content curation (M/W/F) with hashtag and engagement targeting
  • Deployed on DigitalOcean with Nginx, systemd, and Cloudflare DNS/SSL

Where I've worked

Industry 4.0 / Automation Intern (Rotational)
Magna Electric Vehicle Structures
Sep 2023 – Sep 2024

Built a worker-to-station assignment engine (C++/SQLite) with a weighted evaluateFit() scoring function that balanced line familiarity, station expertise, and rank — adopted by the plant and used during real shift changes. Developed an AR-based vision-inspection system for a tablet that performed model-based screw-position recognition and pass/fail logging using Vuforia Model Targets, Inductive Automation Ignition, CSV data pipelines, and Python API scripts. Built managerial monitoring systems with role-based authorization and least-privilege write access, with audit logging of manager changes.

Founder & AI Agent Orchestration
On-Wheels Detailing
May 2020 – Present

Founded and operate a detailing business with paying customers. Wired up Stripe end to end and orchestrated a self-hosted AI agent that designs the site, delivers daily briefings, and alerts on real-time leads.

Academic background

B.S. Computer Science

Wayne State University · GPA: 3.4/4.0
Graduated May 2026

Trustworthy AI coursework: LoRA/QLoRA, RLHF/DPO/GRPO, Red Teaming, Machine Unlearning (TOFU/WMDP), Agentic AI Safety, Grounded VLMs (LISA/GLaMM), Chain-of-Thought Reasoning, HarmBench/SafeChain.

Technologies I work with

Hands-On

PythonPyTorch C++SQL / SQLite JavaScriptDart DockerConformal Prediction Uncertainty QuantificationLLM-as-Judge GPT-4.1-NanoProxmox GPU PassthroughDigitalOcean Nginxsystemd StripeTelegram Bot API Git / GitHub WorkflowInductive Automation Ignition Vuforia Model Targets Machine LearningMySQL Data PipelinesAPI Development Algorithms & Data Structures

Coursework

LoRA / QLoRARLHF / DPO / GRPO Red TeamingMachine Unlearning Grounded VLMsAgentic AI Safety Chain-of-Thought ReasoningHarmBench / SafeChain

Get in touch

Available for opportunities in Detroit, Michigan (EST).

Availability
Open to opportunities
Detroit, Michigan · EST (UTC-5)
Onsite preferred

Work history

A track record across AI, automation, and full-stack engineering.

Industry 4.0 / Automation Intern (Rotational)

Magna Electric Vehicle Structures
Sep 2023 – Sep 2024

Worker-to-station assignment engine (weighted evaluateFit() scoring) adopted by the plant; AR vision-inspection system (Vuforia Model Targets, Inductive Automation Ignition); monitoring dashboards with role-based, least-privilege access.

Founder & AI Agent Orchestration

On-Wheels Detailing
May 2020 – Present

Real detailing business with paying customers. Stripe payments, a self-hosted AI agent, and a Telegram layer for briefings and lead alerts.

CS Graduate — Trustworthy AI

Wayne State University
Graduated May 2026

GPA 3.4. Specialized in AI safety: LoRA, RLHF, red teaming, machine unlearning, grounded VLMs.

Let's talk