Kelvinintech Consulting LLC · Kinston, North Carolina · est. 2024
Hello, I'm Kelvin.
Software. AI. Career systems.I build software and AI systems — and help transitioners do the same with career counseling, résumé & LinkedIn systems, and Tech Affiliates. Based in Kinston, North Carolina; serving Eastern NC and nationwide. Consulting from $76/hr.
Free community meetups in Eastern NC. Network, share goals, and build the room you needed.
About
Isolate the subsystem, trace the signal, fix the root cause — whether it's a crankshaft or a neural network.
10+
3×
32+
120+
Years of systems diagnostics
Excellence Awards (WGU)
Articles on PyTorch & bioinformatics
Tech Affiliates members
1. Diagnose — Diesel Engines
I started my career diagnosing diesel engines — International, Volvo, Freightliner — across shops in Chicago, Charlotte, and Atlanta. That work taught me systematic troubleshooting: isolate the subsystem, trace the signal, fix the root cause.
2. Build — Enterprise Software
I brought that same thinking to software engineering. I earned my B.S. from WGU with three Excellence Awards, built production Blazor and ASP.NET Core systems in healthcare IT, and deployed a full-stack capstone to Azure with 30+ automated tests and CI/CD pipelines.
3. Evolve — AI & Bioinformatics
Now I'm building toward AI. I study PyTorch and deep learning alongside my day job, maintain a 32-article technical blog series, and I'm developing tools at the intersection of software engineering and bioinformatics. My M.S. in AI Engineering starts December 2026 — with a long-term research interest in using generative models to accelerate protein engineering.
Featured projects
AI and ML work first — plus the full-stack capstone that ties my .NET and cloud background together.
DevPulse — Live Multi-API Developer DashboardNEW!
Problem. Developer dashboards that call multiple APIs often fail as one unit — one broken source blanks the whole page — and LLM demos rarely show grounded retrieval before generation.
Solution. A .NET 8 Razor Pages dashboard with independent cards (Weather, HN, GitHub, Crypto, Daily Challenge) plus Ask DevPulse: real RAG over recent HN + GitHub chunks (embeddings + in-memory similarity), then a grounded LLM answer with citations.
Impact. Copyable mid-level ASP.NET pattern — typed models, HttpClient services, DI, CardResult<T> isolation, and retrieve-first RAG that still surfaces sources if the LLM is down — aimed at an Azure App Service demo.
Problem. Job seekers juggle applications, interview dates, recruiter contacts, and outcomes across tools that don’t talk to each other — usually messy spreadsheets.
Solution. Offline-first Windows desktop app (WPF + ASP.NET Core) that organizes search rounds, tracks interview stages, estimates offer probability, exports CSV reports, and syncs SQLite data to a JWT-secured cloud API on SQL Server.
Impact. End-to-end product thinking: domain modeling for a real workflow, client/server separation, offline resilience, and testable business logic — not just a CRUD demo.
Tech: C# · .NET 8 · WPF · MVVM · ASP.NET Core · EF Core · SQLite · SQL Server · JWT · xUnit
Problem. Most breed-classifier demos lean on transfer learning — it’s easy to skip the hard parts of designing capacity, regularization, and a real train/val/test loop on a small dataset.
Solution. Built and trained a custom CNN (no transfer learning) on the Kaggle Dog Breed Identification dataset to classify Scottish Deerhound, Maltese, and Bernese Mountain Dog — data prep, splits, L2-regularized architecture, Colab training, and a Streamlit app for upload → breed + confidence.
Impact. Full training-to-deployment loop that builds intuition around convolutional feature extraction, capacity control, and overfitting — not just a notebook glued to a pretrained model.
Tech: Python · TensorFlow / Keras · CNN · Streamlit · NumPy · scikit-learn · Google Colab · Kaggle
Problem. Some tarantula species look alike — morphology alone doesn’t tell you which are genetically close, or how far apart look-alikes really are.
Solution. An R bioinformatics pipeline that pulls COI DNA barcodes for closely related tarantula species, aligns sequences, computes pairwise genetic distances, and builds a neighbor-joining phylogenetic tree.
Impact. Uses mitochondrial COI barcode sequences to compare look-alike tarantula species, quantify genetic distance, and visualize relatedness — grounding sequence alignment and distance concepts that scale into latent-space / directed-evolution work later.
Tech: R · ape · Biostrings · msa · ggtree · FASTA · DNA barcoding · Phylogenetics
Student Life Tracker (Student Progress Tracker) — WGU D424 Capstone
Problem. Students often manage grades, deadlines, and school finances across separate tools — grades in one place, budgets in another, deadlines nowhere reliable.
Solution. Cross-platform student academic and finance tracker built with .NET MAUI and ASP.NET Core. It unifies terms, courses, assessments, credit-weighted GPA, notifications, and budget tracking behind a JWT-secured Azure API with offline SQLite storage.
Impact. .NET MAUI + ASP.NET Core student life app: GPA analytics, academic planning, and finance tracking with Azure-hosted JWT API — plus unit tests, wireframes, and architecture docs.
Tech: C# · .NET MAUI · ASP.NET Core · EF Core · SQLite · SQL Server · JWT · Azure · MVVM · xUnit
"What a Diesel Engine Taught Me About the Code of Life"
Applied to speak at TEDxRaleigh 2026.
Community snapshots
Conferences, meetups, and people I've learned alongside.
Tech Affiliates kickoff meetup, January 2025James Quick and Kelvin R. Tobias at Render ATLCyrus Harbin and Kelvin R. Tobias at Render ATL
Latest writing
Engineering on Hashnode. Career and AI notes on Substack.
[Substack] Jul 20, 2026 — Creating the Community I’m Seeking I’ve been building Tech Affiliates in Eastern NC for a while now, and if I’m honest, most of it has been me, a laptop, and a lot of trial and error.
[Substack] Jul 12, 2026 — The Room You Walk Into A few weeks ago I taught a prompt engineering workshop to a room of high school students in Kinston, North Carolina.
