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.
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.
Production .NET and data engineering at the core, with an expanding AI and ML toolkit on top.
Insurance, healthcare, automotive, real estate, energy. Different industries, same bar: the system has to work at scale and it can't break.
Not collecting badges. Picking certifications that prove I can build, not just define terms.
Microsoft Certified — cloud concepts, Azure services, security, privacy, compliance, and pricing
Microsoft Certified — AI concepts, Azure ML, computer vision, and NLP services
Building and deploying Azure Cognitive Services, AI solutions, and knowledge mining pipelines
Training, evaluating, and deploying ML and GenAI models with Azure Machine Learning and Microsoft Foundry
Certified — Git fundamentals, GitHub collaboration, repositories, workflows, and project management
Certified — AI-assisted development, prompt crafting, Copilot configuration, and responsible AI usage
Anthropic — building MCP servers that give LLM-powered apps structured access to tools and data
Anthropic — agentic coding workflows, terminal-based AI development, and real-world Claude Code usage
Anthropic — designing and implementing reusable agent skill modules for AI-powered workflows
Anthropic — orchestrating multi-agent systems with subagent delegation and task decomposition
Cross-cloud ML chops: data engineering, modeling, and deployment on AWS
Built around real problems. No toy demos, no tutorial clones. More shipping soon.
Ask plain-English questions against your documents and get cited answers back. A C#/.NET RAG pipeline with swappable providers: the same code runs fully local (Ollama + ChromaDB) or on Azure (OpenAI + AI Search) by flipping one config value. The live demo answers questions about me.
Multi-agent code review for pull requests: an orchestrator fans a diff out to specialized quality, security, and docs agents, then synthesizes their findings into one ranked review. Agents reach real tools (Roslyn, Semgrep, the GitHub API) through MCP. The public, from-scratch version of PR automation I built at work.
An end-to-end NLP pipeline that scores tweet sentiment and flags bot accounts with a 13-feature XGBoost classifier, serving live predictions through a Discord bot. Even back then, trained models were RSA-signed and verified at load time so the inference layer never runs a tampered pickle.
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.
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.
Authored XML API documentation adapting archived XNA reference material, adding platform-specific remarks for DirectX, DesktopGL, iOS, and Android runtime behavior.
Found a hardcoded Azure Cognitive Services endpoint and live API key exposed in a public course sample and submitted the security fix replacing the credentials with placeholders.
Production-grade AI workloads on personal hardware. No cloud bills, no rate limits, no waiting.
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.
Notes, tutorials, and honest reflections from the journey into AI engineering.
