Kelvin R. Tobias — software engineer building toward AI

From OBD Ports to Python Imports

Software engineer building toward AI — applying systematic thinking from freight engines and enterprise systems to neural networks and biological sequences.

WGU B.S. Software Engineering · M.S. AI Engineering (Dec 2026) · CompTIA Security+ · AWS · Linux+ · ITIL 4

View My WorkContact Me

About

Isolate the subsystem, trace the signal, fix the root cause — whether it's a crankshaft or a neural network.
10+
years of
systems
diagnostics
3×
Excellence
Awards
(WGU)
32+
articles on
PyTorch &
bioinformatics
120+
Tech Affiliates
members

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.

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.

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.

Dog Breed Classification CNN screenshot 1 of 1
Dog Breed Classification CNN

Problem

Image classification across 133 dog breeds is hard to do from scratch — you need strong features, enough data, and a path to deployment without drowning in boilerplate.

Solution

Built a convolutional neural network with Keras and TensorFlow using transfer learning, plus a Streamlit UI for real-time predictions from uploaded images.

Impact

End-to-end pipeline from training to local deployment, documented on Hashnode (Part 2 of the series; Part 3 benchmarks PyTorch implementations).

Tech stack

Python
Keras / TensorFlow
Streamlit
Transfer Learning
WalkthroughGitHubBlog
PyTorch Deep Learning Lab screenshot 1 of 1
PyTorch Deep Learning Lab

Problem

Framework tutorials rarely build intuition for autograd, loss landscapes, and why architectures behave the way they do.

Solution

A hands-on lab of 40+ experiments: custom layers, gradient flow, diagnostics, and visualization — built beside long-form writing.

Impact

Pairs directly with 32+ Hashnode articles in the “PyTorch Zero to One” series so readers can reproduce and extend each idea.

Tech stack

Python
PyTorch
NumPy
Matplotlib
WalkthroughGitHubBlog series
Bioinformatics Sequence Toolkit screenshot 1 of 1
Bioinformatics Sequence Toolkit

Problem

Genomic and protein sequences are large and awkward to parse — scripts turn into one-off glue instead of reusable pipelines.

Solution

Python utilities with Biopython and NumPy for streaming I/O, batch processing, and modular analysis steps.

Impact

Reusable foundation aligned with software engineering practice and future work in latent-based directed evolution / protein design.

Tech stack

Python
Biopython
NumPy
WalkthroughGitHub
Student Progress Tracker — Full-Stack Platform screenshot 1 of 1
Student Progress Tracker — Full-Stack Platform

Problem

Students and educators need a centralized, cloud-based academic management system with real-time sync, secure authentication, analytics (weighted GPA, grade projections), and reporting beyond basic offline tracking.

Solution

Built a three-tier system: ASP.NET Core Web API (.NET 8) with JWT auth, EF Core, and Azure SQL; .NET MAUI client (.NET 9) with MVVM; Azure App Service with CI/CD and Swagger; 30+ unit tests (xUnit, Moq, FluentAssertions) at 100% pass rate.

Impact

Production-style capstone: fixed weighted GPA via TDD, isolated DB for parallel tests, consistent API errors and Swagger docs, deployed and maintained on Azure. JWT auth with role-based access.

Tech stack

ASP.NET Core
.NET MAUI
Azure
xUnit
WalkthroughView API DocsView Source

Technical skills

A concise stack — project cards above spell out specifics.

Building with:PythonPyTorchC# / .NETBlazorSQL ServerAzureAWSDockerReactNext.js
Tools & methods:GitCI/CDAgile/ScrumLinuxREST APIsJiraVS Code
Education & certifications (details)

B.S. Software Engineering, WGU — Jan 2026, 3× Excellence Award. Capstone details are in the featured project above.

M.S. AI Engineering, WGU — Starting Dec 2026.

Certifications: Security+ · Linux+ · AWS Cloud Practitioner · ITIL 4 · AWS ML Engineer Associate (in progress).

AWS CCP (Credly)Linux+ (Credly)Security+ (Credly)

Community & Writing

Meetups, long-form technical writing, and a talk pitch in flight.

Tech Affiliates

Monthly meetups, 120+ members, STEM outreach in Eastern NC — labs, templates, and accountability for career changers.

Hashnode Blog
32+ articles · "PyTorch Zero to One" series

Tutorials and build logs aligned with the repos on this site.

Visit the blog
TEDx application
Raleigh 2026

"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 2025
Networking at RenderATL 2024
TechBash 2024 conference session

Let's connect

Open roles, collaborations, or questions about my projects — reach out async or jump on a call.

Usually reply within 48 hours · Prefer async? Use the form.

Send a messageJump on a call
LinkedInGitHubBlogRésumé
KRT