Portfolio

Professional case studies.

Selected examples of turning difficult backend, computer-vision, and engineering-effectiveness problems into practical results.

backendapplied AIautomationreliabilityleadership

Applied AI · Automation

Automated Store Calibration

A Python calibration platform that turned a complex, engineer-led computer-vision setup into a repeatable workflow.

Problem
Every new drive-through store required engineers to interpret camera tracks, place markers, and tune lane geometry by hand. The process was slow, fragile across store layouts, and pulled senior engineers into recurring setup work.
Outcome
Reduced initial store setup effort by 50%, from 40 to 20 engineer-hours per store, while creating a maintainable foundation for handling new layouts and calibration edge cases.
PythonOpenCVYOLOscikit-learn
Read case study

Computer Vision · Reliability

Vehicle Tracking Reliability

Detector and tracking improvements for a multi-camera drive-through platform operating on noisy real-world video.

Problem
Missed detections disrupted vehicle histories across entry, merge, and exit zones. The resulting gaps reduced the accuracy of downstream timing and analytics and were difficult to reproduce consistently.
Outcome
Reduced missed vehicle detections by approximately 77%, from 22 to 5 per 100 vehicles, improving the stability of downstream tracking and operational metrics.
PythonYOLOv8/11OpenCVPyTorch
Read case study

Engineering Effectiveness · Technical Leadership

Test Foundation & Modular Architecture

A unified pytest/CI foundation and a coordinated modular refactor that made a legacy computer-vision codebase safer to change.

Problem
The core service had fragmented tests, only 10% coverage, and no automated pull-request validation, so engineers had little confidence that changes stayed isolated. Core behavior had also grown across duplicated paths, making changes risky and obscuring the boundary around proprietary components needed for a patent application.
Outcome
Increased automated test coverage from 10% to 34% with automated pull-request validation, and delivered a more modular core with a cleaner technical boundary for patent-related work.
PythonpytestJenkinsAWS EC2
Read case study

Technical Leadership · SaaS

From Sole Developer to a Product Team

Grew a SaaS guidebook platform from a single developer to a product engineering team while re-architecting the guest experience.

Problem
I joined as the only developer on a tightly coupled, server-rendered Django monolith (templates plus jQuery) with a large backlog of customer-requested features. One developer could not maintain the platform and build its next version at the same time.
Outcome
Increased engineering throughput by at least 2x and supported approximately 2x product revenue growth over one year, delivering a fully separated, redesigned Vue.js guidebook with frequent, low-risk releases.
PythonDjangoDRFMySQL
Read case study

Backend Integration · SaaS

Production Partner Integration for a Revenue Platform

A production Seismic integration that let customers connect an existing account and bring partner data into a sales-performance platform without re-entering it.

Problem
Ambition's customers wanted their existing Seismic data inside Ambition's metrics engine without duplicating setup. The work also supported a company-level OKR to establish a strategic partnership with Seismic, so it had to be production-grade rather than a prototype.
Outcome
Released the Seismic integration to production in direct response to customer demand and supported the company-level partnership OKR, delivered as a complete increment spanning backend, frontend setup flow, documentation, and automated test coverage.
PythonDjangoDRFPostgreSQL
Read case study