AI Engineering & Automation
LLM integrations, agent orchestration, tool calling, and AI-augmented development workflows — from prototype to production.
Services
Consulting and delivery centered on systems, outcomes, and operational reliability
Cloud & Backend Architecture
Scalable APIs, serverless systems, and secure integrations on AWS and Azure.
Mobile Platform Development
Cross-platform mobile applications integrated with real-world operational systems.
Legacy System Modernization
Upgrade aging .NET or enterprise platforms to modern cloud architecture without disrupting operations.
Fractional CTO / Technical Advisory
Architecture reviews, system design guidance, and senior engineering oversight.
Featured Platform Impact
Long-term delivery and measurable business value
DiSC Mobile Logistics Platform
Cross-platform logistics mobility and document intelligence platformProblem
Transportation companies needed mobile workflows for drivers, document capture, and GPS-based stop tracking integrated with existing logistics systems.
Solution
Built a cross-platform logistics mobility platform with document capture (PDF-to-TIFF, deskew, crop), GPS stop tracking, and backend freight integration.
Impact
- Used in real-world freight operations
- Handles GPS stop tracking, driver workflows, and document capture / cleanup for proof-of-delivery printing
Android / iOS
Flutter
Xamarin
C#
ASP.NET
.NET WCF
Python
SQL Server
Technical Capabilities
Depth across AI systems, cloud architecture, mobile delivery, and backend engineering
AI & Automation
LLM application development, computer vision, OCR, tool calling, multi-agent systems
AI-Augmented Development
Building software with LLM-powered coding agents and AI-driven workflows.
Tools: Claude Code, Codex, Cline, Antigravity IDE, GitHub Copilot, LM Studio, Ollama, MCP servers
Mobile Platforms
Flutter, Xamarin, MAUI.NET, iOS, Android
Backend Systems
Node.js, ASP.NET Core, TypeScript, C#, Python, real-time APIs
Cloud Infrastructure
AWS, Azure, Docker, PostgreSQL, SQL Server, DynamoDB
Technical Proof
Selected visual walkthroughs showing applied computer vision, AI extraction, and MCP-based tooling
⬡ Stage 1
Detect — Blueprint Object Detection
Streamlit demo detecting countertops, sinks, and appliances in architectural blueprints utilizing a trained Faster R-CNN model.
◈ Stage 2
Scale — OCR Measurement Extraction
Extracting blueprint scale via OCR (docTR) to compute real-world dimensions, areas, and generate material cost estimates.
◉ Stage 3
Segment — Instance Segmentation
Pixel-perfect instance segmentation masks isolating exact countertop shapes for area computation and material estimation, leveraging a trained Mask R-CNN model.
Architecture: Faster R-CNN and Mask R-CNN utilized as the core backbones for detection and segmentation respectively · Training: 10,000+ annotated blueprint images · Infra: Model training executed on large GPU clusters · Demo: Streamlit interactive frontend
ScraperAI Platform
⚙ Stage 1
Dashboard & AI Provider Setup
Central dashboard for managing AI providers, prompts, scraping jobs, API keys, and analytics. Configure providers like OpenRouter and LM Studio with model selection and API key management.
✎ Stage 2
Prompt Engineering & Configuration
Create and manage scraping prompts with target URLs, custom instructions, system prompts, provider/model selection, output format (JSON/XML), and fetch method (headless browser or direct).
▶ Stage 3
Execution, Monitoring & Results
Monitor crawling jobs with status tracking, filtering, and pagination. View detailed job results including AI processing metrics (tokens, cost, confidence) and validated structured JSON output.
Backend: .NET 8 / ASP.NET Core · Frontend: React SPA · Scraping: Headless browser (Playwright) · AI: OpenRouter, LM Studio, Anthropic, OpenAI providers · Output: Structured JSON/XML with validation
MathMCP Server
∑ The Challenge
Complex DSP Concepts
Excerpt from a Digital Signal Processing textbook. The material is dense, mathematical, and difficult to parse for beginners or high school students.
✓ The Solution
AI Simplification (LM Studio)
MathMCP server connected to LM Studio local LLM. The agent ingests the textbook image, simplifies the concepts for a high school level, and generates practice questions.
Tech: Model Context Protocol (MCP) · Model: Local LLM (LM Studio) · Input: Visual / OCR + Text · Goal: Educational simplification & accessibility
Selected Case Studies
Representative consulting and architecture work in a problem, solution, and impact format
Basil / Annie AI Sales Automation
Problem
Dealership teams needed faster lead capture, qualification, and follow-up inside existing CRM workflows.
Solution
Built chat capture, VIN-aware context handling, lead routing, and TypeScript agent skills for SMS, email, and CRM actions.
Impact
Automated lead qualification and follow-up across SMS, email, and CRM — reducing manual touchpoints in live dealership workflows.
Core Technologies: TypeScript, Node.js, CRM integrations, AI workflow automation.
InCommercial AI Chat Agent
Problem
The platform needed stronger security, more reliable auth flows, and better real-time AI interaction.
Solution
Engineered JWT auth with refresh token workflows, improved streaming behavior, and refined the chat product experience.
Impact
Hardened authentication and AI streaming for a commercial real estate platform, enabling production launch with enterprise-grade security.
Core Technologies: JWT auth, streaming AI UX, backend hardening, web application delivery.
Additional Projects
Selected builds across AI tooling, mobile platforms, and serverless architecture
SmartCoder — AI Developer MCP Server
Developer infrastructure for AI coding agents and local environmentsMCP server for semantic code search, automated file analysis and editing, and OCR-based visual inspection workflows designed for local-model usage.
PythonFastMCPOpenCVPyTesseract
Task3r — AI Task Management Platform
Serverless conversational task platform (In Development)AI-assisted task operations built on a serverless AWS backend with conversational workflows, identity management, and cross-platform delivery.
FlutterAWS LambdaAPI Gateway
CognitoBedrockS3
Visit task3r.com →
Steward Mobile
Field service operations platformMobile platform for field service scheduling, dispatch, and job tracking with an enterprise ASP.NET Core backend.
FlutterASP.NET Core
Engineering Notes
Short articles and insights about building production systems
Designing Cost-Efficient AI Agent Architectures
Notes on making agent systems useful in production without letting inference cost dominate the product.
Read article →AI Integrations for Production Applications
What changes when retrieval needs reliability, latency control, and operational ownership.
Read article →Integrating AI Into Existing SaaS Platforms
Practical approaches for adding AI to established products, workflows, and customer-facing systems.
Read article →Modernizing Legacy .NET Systems
How to upgrade critical older platforms incrementally without breaking the business around them.
Read article →Let’s Talk
I work best with companies and founders who need senior engineering across AI, backend, mobile, and architecture.
Contract & Full-Time Roles
AI Integration & Automation
Software Architecture
Full Stack & Mobile
Computer Vision