Hello, I'm Aleksandr

Lead Product Manager, AI Platforms & Agents: hands-on across agents, RAG, MCP, and production Python

Based In Limassol, Cyprus
Open to Select Opportunities
I'm open to conversations about senior product and product-engineering roles in applied AI: agent platforms, developer tools, and model evaluation. Collaborations and professional advice are always welcome. Based in Cyprus, open to relocation for the right opportunity.
02 / SKILLS

The craft, earned.

01 SKILLS

Artificial Intelligence

LLM engineering across retrieval-augmented generation with vector and hybrid search, agent and retrieval orchestration on LangChain and LangGraph, Model Context Protocol tooling, LangSmith observability, and evaluation-driven delivery of production AI systems.

Read More
02 SKILLS

Model Context Protocol

MCP end to end — servers published to PyPI and the official registry, clients wired into agent runtimes across four transports, an authenticated gateway in front of internal servers, and protocol-level defects reported upstream, one of them already fixed and released.

Read More
03 SKILLS

Python

Production Python for AI systems — async FastAPI and FastMCP services, LangChain and LangGraph retrieval pipelines, tested with pytest and shipped through automated release and deployment pipelines.

Read More
04 SKILLS

Claude Code

Professional-grade command of Claude Code — orchestrators, subagents, dynamic workflows, hooks, skills, slash commands, MCP, and context engineering — applied to production multi-agent development environments.

Read More
05 SKILLS

AI Product Management

AI products taken from problem selection to adopted production systems — a measurable quality bar set up front, evaluation run before wide release, platform framing that compounds, and outcomes stated in numbers the products themselves published.

Read More
06 SKILLS

LLM Engineering

Building LLM systems that survive production — structured output, per-stage fallback and retry ladders, model tiering by task, tracing wired into the serving path, and a measured quality bar before anything ships wide.

Read More
03 / GITHUB

The work, in public.

2.7k commits, 805 merged pull requests, 18 external repositories, 12 organizations, 83 active days in the last 90plus 8,821 private contributions not shown — every number here is a floor, not a ceiling

7,907 contributions last 12 months

  • Python 74.0%
  • HTML 12.1%
  • JavaScript 10.9%
  • Shell 1.1%
  • Batchfile 0.8%
  • HCL 0.6%
  • TypeScript 0.3%
  • PLpgSQL 0.1%

on GitHub

04 / EXPERIENCE

Where the work lived.

05 / PROJECTS

Projects, released.

01 Enterprise AI Platforms

AIR API — AI Retrieval API

An AI-driven retrieval platform that serves grounded answers from corporate knowledge sources (Help Centre + cTrader Admin Guide) to any AI assistant, support automation, or team workflow inside Spotware — through a REST API and a standards-compliant MCP server, with automatic twice-daily content refresh.

Active — Present
02 Enterprise AI Platforms

Claude Code Gateway

The corporate LLM gateway between every engineer's coding agent and the upstream model providers: provider routing and failover across multiple AI labs, per-user request, token, and cost accounting at API prices, an authenticated admin surface with usage analytics, and centrally administered usage governance — rebuilt from an open-source foundation into a corporate-grade service.

Active — Present
03 Applied AI Products

AILA — AI Localisation Assistant

An AI-powered localization system built at Spotware that combines approved terminology and translation memory with strong AI models to deliver fast, high-quality, on-brand translations at scale, dramatically improving time-to-market for localization across regions.

Active — Present
04 Open Source & Experiments

MCP Context Server

A high-performance Model Context Protocol server that gives LLM agents a durable, searchable memory layer beyond the context window. Thread-scoped storage over SQLite or PostgreSQL, with semantic, full-text, and hybrid search, cross-encoder reranking, pluggable embedding and summary providers, metadata filtering, and batch operations — all behind a standard MCP interface.

Active — Present
06 / CERTIFICATIONS

The papers, stamped.

07 / LATEST POSTS

Notes, in long form.

Agent Experience: Preparing Your Site for Its Second Reader

Agent Experience: Preparing Your Site for Its Second Reader

Every page on your site is two documents: the one a browser renders for people and the one a parser reads. AI agents read the second one. Here is what I learned making this site legible to them -- and what a machine reader finds on the personal sites of eight of the best-known people in AI, from a hidden Order of the Unicorn to a robots.txt that redirects into itself forever.

Dynamic Workflows: When the Agent Writes Its Own Harness

Dynamic Workflows: When the Agent Writes Its Own Harness

For a few weeks now, Claude Code has been writing its own multi-agent harness for each task -- and it quietly retired the orchestration code I used to maintain by hand. Here is what changed, the patterns worth knowing, and the research idea I think sits underneath it.

MCP Context Server: Persistent Memory for Your AI Coding Agents

MCP Context Server: Persistent Memory for Your AI Coding Agents

Your AI coding agent loses its plan every time the context window compacts. MCP Context Server fixes that with persistent, searchable memory -- one Docker command and your agents remember everything.