GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — MarkhamLee - Overview

@MarkhamLee MarkhamLee Follow
More
  • Overview
  • Repositories
  • Projects
  • Packages
  • Stars
  • Sponsoring
@MarkhamLee
MarkhamLee
Follow
View MarkhamLee's full-sized avatar

Markham Lee MarkhamLee

Follow
Engineer building platform agnostic AI, vision, and data systems; event driven pipelines and training computer vision models.
15 followers · 11 following
  • Seattle, WA
  • 08:39 (UTC -08:00)
  • in/markhamlee

Achievements

Achievement: StarstruckAchievement: Pull Sharkx2Achievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: Public Sponsor

Achievements

Achievement: StarstruckAchievement: Pull Sharkx2Achievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: Public Sponsor
More
  • Overview
  • Repositories
  • Projects
  • Packages
  • Stars
  • Sponsoring
MarkhamLee/README.md

Hi there 👋

I’m a data and machine learning engineer specializing in computer vision, data infrastructure, and MLOps. I build and deploy platform‑agnostic AI, computer vision, and data‑driven microservices for cloud, edge, and on‑premises environments. My work centers on Docker‑based, event‑driven pipelines using AWS ECS, Fargate, SNS, and SQS for data ingestion, model training, and inferencing.

My machine learning experience includes turning R&D concepts into scalable, production‑ready systems and training and fine‑tuning computer vision and multimodal models. Current projects revolve around image quality enhancement, automated data pipelines, and integrating detection, pose, and vision‑language models to improve accuracy and robustness

My core languages are Python and TypeScript, with R and SQL for analysis, and C/C++ for embedded and sensor‑driven systems.

  • 👯 Open to collaborating on open‑source data, machine learning, and embedded projects.

  • 📫 Connect on LinkedIn to discuss full‑time, contract, or research collaborations. LinkedIn

Pinned Loading

  1. internet-and-iot-data-platform internet-and-iot-data-platform Public

    Data engineering layer for a k3s-based private cloud (https://github.com/MarkhamLee/k3s-powered-private-cloud-homelab), ingesting and processing data from DevOps, finance, IoT, and external APIs, w…

    Python 7 6

  2. k3s-powered-private-cloud-homelab k3s-powered-private-cloud-homelab Public

    Documentation, IAC and custom code for a K3s based private cloud

    Python 4 1

  3. vision-pipeline-benchmarks vision-pipeline-benchmarks Public

    Multi-modal computer vision inference pipeline benchmarks and reference architectures

    Python

  4. computer-vision-demo-reel computer-vision-demo-reel Public

    Computer vision demos related to classification, object detection and segmentation for commercial and industrial use cases.

    Python

  5. Facial-Recognition-Facenet-Pytorch Facial-Recognition-Facenet-Pytorch Public

    Docker and Flask based API layer + data ingestion pipeline for the Facenet-PyTorch facial recognition library. I.e. simple ML deployment for matching pairs of photos

    Python 2 3

  6. HardwareMonitoring HardwareMonitoring Public

    PC Gaming Sensor Panel & General Hardware monitoring for Linux (x86 and ARM64) and Windows via Libre Hardware Monitor, psutil, gputil and NVIDIA smi-queries for display on a Grafana dashboard. Also…

    Python 18

Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.

Uh oh!

There was an error while loading. Please reload this page.

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.