Hello, I'm Aleksandr
Lead Product Manager, AI Platforms & Agents: hands-on across agents, RAG, MCP, and production Python
The craft, earned.
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.
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.
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.
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.
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.
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.
The method, stated.
I turn frontier AI capabilities into reliable products and reusable platforms.
Product ownership
I start with the problem: users, constraints, success criteria, and the adoption path — before any code.
Platform thinking
I build reusable capabilities — retrieval, gateways, agent runtimes — rather than isolated AI demos.
AI-native engineering
Coding agents multiply my implementation speed; architecture, review, and accountability for outcomes stay mine.
Evaluation and verification
I define invariants, regression tests, and quality gates before trusting model or system behavior.
Production and adoption
A system counts when it is deployed, observed, supported, and measurably used.
The work, in public.
Where the work lived.
operating as AI Product & Platform Lead
operating as Requirements & Agile Delivery Lead
Projects, released.
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.
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.
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.
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.
The papers, stamped.
Build Small Hackathon 2026
Certificate of participation in Build Small, a Hugging Face × Gradio hackathon celebrating small, local, open-weight models — building real, tinkerable apps powered entirely by models under 32B parameters.
Professional Scrum Master I (PSM I)
The certification validates my knowledge of the Scrum framework, the Scrum Master accountabilities and how to apply Scrum.
Develop Your Skills as a Software Project Manager
A validation of acquiring in-depth knowledge and practical skills in managing software projects, focusing on Agile and Scrum methodologies, risk assessment, team collaboration, and effective communication.
Atlassian Agile Project Management Professional Certificate
A comprehensive certification validating expertise in Agile project management principles and proficiency in Atlassian tools for effective project execution.
Notes, in long form.
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
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.
Field Notes: Building a Chest X-ray Draft Auditor with Two Tiny 4B Models — MedGemma and NVIDIA Nemotron
A Field Notes write-up on building a chest X-ray draft auditor from open data alone: two tiny 4B models, a deterministic comparator, and the evaluation-integrity lesson that nearly cost me the better model.
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.