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.
What I've built
Research-to-prototype systems at the intersection of AI and infrastructure.
ConformalBMI — Uncertainty-Aware Body Mass Estimation
Translated published BMI-estimation research (Digital Scale, Sui et al., Manichand et al., Jin et al.) into a working estimator — a Squeeze-and-Excitation DenseNet (SE-DenseNet121) in PyTorch, extended with split conformal prediction for calibrated uncertainty and a GPT-4.1-Nano reasoning layer that explains each estimate.
- Research-to-prototype: built on peer-reviewed BMI estimation literature, extended with conformal prediction and LLM-based reasoning
- Split conformal prediction for distribution-free uncertainty — 90% intervals with 90.4% empirical coverage on 620 held-out samples
- 2.81 BMI-point MAE (11.56% MAPE) on a 620-sample held-out test set (Celeb-FBI, 7,208 real images)
- GPT-4.1-Nano LLM-as-judge explains each estimate and flags edge cases in plain English
Research Foundation
Built on established BMI estimation research and extended with split conformal prediction for calibrated uncertainty and GPT-as-Judge reasoning:
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
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
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
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
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.
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
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
Coursework
Get in touch
Available for opportunities in Detroit, Michigan (EST).
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)
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
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
GPA 3.4. Specialized in AI safety: LoRA, RLHF, red teaming, machine unlearning, grounded VLMs.