Selected work,
2018-present.

A working archive of projects in computer vision, 3D perception, and the infrastructure that keeps them honest.

11 projects · 11 total

Tracking - Multi-Camera Multi-Person Tracking

Real-time multi-camera person tracking for customer behavior analysis and site security, with re-identification across non-overlapping views. Pose triangulation and appearance embeddings raised inter-camera mAP from 40% to 74% on an open-set benchmark.

Computer Vision 3D Vision Deep Learning
2025
Tech Lead
PyTorch · Docker

VMS - Live-Camera Anonymization Software

Low-latency face and license-plate anonymization for RTSP streams, integrated directly into Milestone VMS through the AI Bridge. Shared decoders and batching improved load balancing and kept GPU utilization high under concurrent camera load.

Computer Vision Software Engineering
2024
Engineer
C++ · FastAPI · PyTorch

Cargo - Volume Measurement

A real-time 3D reconstruction and contour-fitting pipeline using depth cameras and Open3D. Built as a multi-process pipe-and-filter system for airline cargo measurement at operational speeds.

3D Vision Computer Vision
2023
Lead
C++ · Python · Docker · Qt

Data - Geo-Data Management Tool

A PostgreSQL and PostGIS platform for curated dataset storage, geographic querying, and sampling. Included a Django backend, Celery workers for heavy compute jobs, and a client library for dataset access.

Data Engineering
2023
Engineer
Django · PostgreSQL · Python

Safety - Model Robustness Tests for AVs

Kubernetes-based model serving, benchmarking, and safety evaluation for autonomous vehicle ML products. Added new safety performance indicators and benchmark workflows for real and synthetically perturbed data.

Deep Learning Software Engineering
2022
Engineer
Go · Kubernetes · PyTorch

Pipeline - Multi-Task Deep Learning

A single training framework for classification, detection, and segmentation. Reworked CPU-heavy metrics with multiprocessing and Cython, pushing overall GPU utilization above 90% in training and inference.

Deep Learning Computer Vision Software Engineering
2021
Engineer
Python · TensorFlow · Docker

Media - Processing Service at Roposo

A media-processing service for compression, metadata analysis, and beautification. Optimizations cut infrastructure cost by 70 percent while enabling plagiarism analysis and adaptive SSIM-based compression.

Computer Vision Software Engineering
2020
Engineer
Java · OpenCV · AWS

Resell - Product Form at Amazon

A high-performance DynamoDB-backed product form workflow that reduced payload size by 99.5 percent and improved form completion rate by 5x on mobile-heavy usage.

Software Engineering
2019
Engineer
Java · DynamoDB

Catalog - Labeling Quality Platform

A clustering-based quality platform for catalog labeling review with human-in-the-loop analysis. Reduced catalog quality checks from weeks to under an hour.

Data Engineering Machine Learning
2019
Engineer
Python · Spark

Turbulence - Removal Module

A non-rigid registration-based atmospheric turbulence removal module for long-range imagery. CUDA and pipe-and-filter optimizations delivered a 240x speedup and made the system usable in real time.

Computer Vision
2022
Engineer
C++ · OpenCV · Qt

Wide Area - Tracking Module

A wide-area tracking system with PTZ control, multi-camera stitching, and change detection for CCD and infrared camera setups in real-time operational environments.

Computer Vision Software Engineering
2018
Engineer
C++ · OpenCV · Qt