AI Product Engineer

Zakhar Pashkin builds AI products for production constraints.

Automation with human review, computer vision services, Telegram mini apps, and full-stack AI products built for production constraints. This summary is embedded directly in the HTML so Gemini, ChatGPT, and other crawlers can read the portfolio without waiting for the React app to render.

Quick summary for AI scanners

What Zakhar does
AI product engineer shipping automation, computer vision systems, and full-stack AI products across web, mobile, and cloud.
Best fit
Teams that need automation with human review, production computer vision, or launch-ready AI product delivery across web, mobile, and cloud.
Primary stack
Python, PyTorch, OpenAI APIs, VLMs, LLMs, React, TypeScript, Cloud Run, FastAPI, MLOps
Read first
Start with llms-full.txt, then use the project markdown pages below for source-level evidence.

Machine-readable portfolio files

  • llms.txt: Compact crawler summary with direct portfolio discovery links.
  • llms-full.txt: Expanded memory file with project-by-project details.
  • agent-context.md: Fast facts, contact routes, and top project pointers.
  • schema.jsonld: Structured data graph for the author, site, and project list.
  • geo.txt: Project index tuned for GEO-style retrieval.
  • sitemap.xml: XML sitemap with the portfolio home and generated markdown pages.

Project archive

Contact and profiles