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.
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.
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.
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 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.
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.
Retrieval systems built as shared platforms — hybrid vector and full-text search fused with RRF, cross-encoder reranking, query decomposition, parent-document storage, and multilingual query handling, with quality calibrated from production retrieval telemetry.
Compiled LangGraph state graphs with conditional routing in shipped systems, plus checkpointed state, middleware, and human-in-the-loop interrupts — built and tested — feeding an agent platform in development where agents are stored configurations.
Async FastAPI services for AI workloads — one application serving REST and MCP from a shared core, per-surface authentication, Pydantic contracts end to end, and containerized deployment to Kubernetes behind CI.
MCP servers built on FastMCP — an async tool layer behind a PyPI-published memory server, a production system-of-record server, and an HR server designed fail-closed — with tool surfaces curated for agents rather than generated from an API.
Relational database design and SQL, plus hands-on work with the SQLite, PostgreSQL, MongoDB, and Chroma stores behind AI retrieval systems I build — pgvector and sqlite-vec, full-text, semantic, and hybrid search.
Deploying containerized Python AI services on Kubernetes — Helm values for autoscaling, probes, ingress and resource budgets on a shared platform chart, an authored Helm chart for an open-source MCP server, and staged GitLab CI release pipelines.
Hands-on CI/CD across GitHub Actions and GitLab CI — quality gates on every change, conventional-commit release automation that versions, changelogs, and publishes packages and container images, and Helm-based deployments to Kubernetes.
Experience in leveraging Docker for local development and CI/CD pipelines, including writing Dockerfiles for Python application deployment.
Expertise in Google Cloud services, focusing on application scalability, security, and efficient cloud infrastructure management.
Expertise in utilizing Cloudflare for DNS management, security, and web performance.
Advanced use of Terraform for efficient cloud infrastructure provisioning and management, including custom module development for DNS settings in Cloudflare.
Expertise in RESTful API design and understanding of client-server interactions, and API documentation with OpenAPI.
Expertise in OAuth 2.0 protocols, including comprehensive understanding of authentication flows, JWT utilization, and essential security measures.
Product and technology leadership since 2011 — building and running teams, owning delivery from head-of-technology to AI-product-lead roles, hiring against a senior bar, and driving organization-wide adoption of what ships.
Expertise in engaging and managing relationships with stakeholders across all levels.
Expertise in designing and implementing complex system architectures for AI solutions, focusing on scalability, interoperability, and optimal performance.
Competent in transforming business ideas into structured, actionable plans using BPMN and UML, adaptable to various modeling tools.
Experience in manual and automated testing, including UI, functionality, unit testing in Python, and API testing, to uphold software quality.
Professional Scrum Master with comprehensive knowledge and practical application of Agile principles, specializing in Scrum and Kanban to enhance project adaptability and efficiency.
Certified mastery in Scrum, leveraging its principles for optimal team performance and project agility.
Practical experience in using Hugo for the development of secure, performant, and customizable websites.
Long-standing experience in SEO, optimizing web presence through comprehensive strategies, including effective use of Google Search Console.
Certified expertise in Google Analytics, from standard to custom reporting, and sophisticated implementation for detailed event tracking.
A working command of HTML, CSS, and JavaScript — semantic accessible markup, a token-driven Tailwind v4 design system, and dependency-free vanilla scripts — applied across production sites and reusable Hugo modules.
Strong reading, listening, grammar, and vocabulary skills, verified by CEFR B2 certification, with dedicated efforts towards enhancing speaking proficiency.
Native speaker with a deep cultural and linguistic understanding of the Russian language.
Python
Claude Code
LangGraph
FastAPI
Kubernetes
Docker
Google Cloud
Cloudflare
Terraform
Scrum
Hugo
Google Analytics