Software Engineer × AI Builder

Seven years of enterprise .NET, now pointed at AI

I build high-volume production systems in C#, React, and SQL Server. Lately, I've been wiring those same skills into LLMs, RAG pipelines, and multi-agent workflows, all running on local GPU hardware.

DGX Spark Online
~/ai-lab
ollama run llama3
pulling model... ✓
loading weights on DGX Spark...
ready. inference at 127 tok/s
 
// RAG pipeline active
dotnet run --project VonAI.AgentOrchestrator
agents initialized: [planner, coder, reviewer]
connected to SQL Server ✓
workflow status: operational

Engineer first.
AI-obsessed second.

For the past 7+ years, I've been building the kind of software that can't go down: C# APIs, SQL Server architectures, React frontends, all running at scale for companies that process serious volume. One system I optimized handled $1.5 Trillion in historical insurance data. Another tool I built cut a team's monthly support tickets by 90%.

I've worked across healthcare platforms for seniors, a workforce tracking system serving 11,000 daily users at the world's largest BMW plant, and AI-driven injury evaluation services used by 18 of the top 20 US insurance carriers.

Now I'm taking all of that production discipline and applying it to AI. I'm building RAG apps, experimenting with multi-agent systems, fine-tuning open models on my own NVIDIA DGX Spark, and stacking certifications that actually reflect hands-on skill.

7+
Years in Production Software
$1.5T
Insurance Data Processed
90%
Support Tickets Reduced
11K
Daily Users Supported

What I build with

Production .NET and data engineering at the core, with an expanding AI and ML toolkit on top.

Backend & Data

C# / .NET Core ASP.NET MVC T-SQL SQL Server Entity Framework Dapper LINQ REST APIs

Frontend & UI

React.js React Native JavaScript HTML / CSS jQuery Responsive Design

AI & ML

Azure AI Services GitHub Copilot LLM Integration RAG Pipelines Prompt Engineering Ollama Local Inference Agent Workflows

Cloud & DevOps

Azure Cloud Cloudflare IIS Git GitHub Actions Docker PowerShell

Databases

SQL Server MySQL PostgreSQL Data Modeling Query Optimization SSIS / SSRS

Tools & Infrastructure

Visual Studio Postman SoapUI JAMS WINSCP NVIDIA DGX Spark Python

Where I've shipped

Insurance, healthcare, automotive, real estate. Different industries, same bar: the system has to work at scale and it can't break.

Software Engineer II · Fortis Technologies

Apr 2022 — Present
  • Built and launched a cloud-based injury evaluation service that uses AI and biomechanical analysis to review bills, assess settlements, and speed up claims processing for major carriers.
  • Optimized high-volume C# .NET data applications backed by advanced SQL Server logic, processing and validating over $1.5 Trillion in historical insurance data with help from GitHub Copilot.
  • Kept 24-hour inbound/outbound data and web services running for 18 of the top 20 US insurance companies, supporting both internal tools and customer-facing apps in an Agile environment.

Software Engineer · HomeCare

Dec 2021 — May 2022
  • Designed and built enhancements for HomeCare Connect, an enterprise web portal delivering Medicare-certified home health and senior care services.
  • Wore both the product owner and developer hats to design and ship a C# .NET bulk data update tool that cut the team's monthly support ticket volume by 90%.

Software Engineer · Powerserve

May 2019 — Jan 2022
  • Shipped full-stack features across multiple enterprise web and mobile apps in ASP.NET MVC and .NET Core for clients including MAU Workforce Solutions, BMW, and William Raveis Real Estate.
  • Built critical features for a C# .NET application that tracked 11,000 daily users at the largest BMW Group plant in the world. Zero room for downtime.
  • Wrote a custom C# .NET and T-SQL pipeline to automate high-volume marketing data imports, giving BMW's marketing team the ability to generate filtered, targeted reports on demand.

Certs that mean something

Not collecting badges. Picking certifications that prove I can build, not just define terms.

AI
900

Azure AI Fundamentals

Microsoft Certified — covers AI concepts, Azure ML, computer vision, and NLP services

✓ Earned
AI
102

Azure AI Engineer Associate

Building and deploying Azure Cognitive Services, AI solutions, and knowledge mining pipelines

In Progress
DP
100

Azure Data Scientist Associate

Training, evaluating, and deploying ML models with Azure Machine Learning

Planned
AWS
ML

AWS Machine Learning Specialty

Cross-cloud ML chops: data engineering, modeling, and deployment on AWS

Planned

Built to learn. Shipped to prove it.

Each one solves a real problem. No toy demos, no tutorial clones.

📄 DocQuery RAG

Ask plain-English questions against technical docs and get grounded answers back. C# backend handles the orchestration, React frontend keeps it clean, and embeddings run locally on DGX Spark so nothing leaves the machine.

C# React LangChain ChromaDB Ollama

🤖 AgentForge

A multi-agent framework where a planner, coder, and reviewer work together to break down complex tasks. LangGraph handles the workflow graph, .NET ties it all together, and the agents actually argue with each other before shipping an answer.

.NET 8 LangGraph Llama 3 DGX Spark

🔧 MCP Toolkit

A Model Context Protocol server that gives LLM-powered apps safe, structured access to SQL Server databases and internal tools. Think of it as a permissions layer between your AI agent and your production data.

C# MCP SQL Server Azure

⚡ SparkBench

Benchmarking suite for local LLM inference on the DGX Spark. Measures throughput, latency, and memory across different quantization levels and model families so I know exactly what this hardware can handle.

Python vLLM TensorRT-LLM CUDA

Local AI infrastructure

Production-grade AI workloads on personal hardware. No cloud bills, no rate limits, no waiting.

Platform
NVIDIA DGX Spark
GPU Memory
128 GB Unified
Inference Stack
Ollama + vLLM
Models Running
Llama 3, Mistral, Phi
Status
● Online
Uptime
99.7%

Why local?

Running models on my own hardware means I can experiment without watching API costs climb, keep data completely private, and iterate on model behavior without hitting rate limits or usage caps. When you own the compute, you move faster.

The DGX Spark's unified memory lets me load models that would normally require multiple consumer GPUs. That means real fine-tuning and proper benchmarking, not just running demos.

  • Local LLM inference and benchmarking
  • Fine-tuning open models on domain data
  • Multi-agent workflow development
  • RAG pipeline prototyping
  • Model quantization experiments

Let's build something

Open to full-time roles, contract work, and collaborations where AI meets real engineering problems.