— PORTFOLIO

SENIOR AI PLATFORM ENGINEER

I build and operate multi-agent platforms for governed AI-assisted delivery.

01 — ABOUT

Background & Approach

I spent 6+ years building systems that do not break — enterprise Java, Spring Boot, and distributed microservices at GlobalLogic. That foundation shapes the multi-agent platforms I build today: durable workflows, explicit approval boundaries, local-first memory, observability, and failure-aware execution. Those are engineering constraints, not optional polish.

At GlobalLogic, I architected a config-driven multi-agent execution harness for an internal LLM platform: LangGraph state graphs across 41 agents, deterministic and LLM-routed execution paths, and validation at startup and in CI for unresolvable skills, invalid routing graphs, and cycles. The validator exposed approval gates that could never fire and agents reserving model budget for calls they never made — turning agent configuration into something testable and operable. I apply the same platform mindset to my self-hosted multi-agent development platform for AI-assisted delivery and local infrastructure operations: bounded specialist agents across multiple LLM providers, durable Git-backed local-first knowledge, explicit operator confirmation, and a Node.js, TypeScript, and React operations surface for live infrastructure, agent activity, scheduled automation, and evidence-backed delivery records.

CURRENTLY SEEKING

I am looking for a product company where AI architecture and developer experience are the product — not a thin wrapper around an API call. I thrive designing multi-agent orchestration, evaluation harnesses, MCP-enabled tools, and reliable AI delivery workflows with observability, cost signals, and fault tolerance built in. Remote only. Contract or full-time.

02 — SKILLS

Technical Stack

Protocol Engineering

MCP (Streamable HTTP, RFC 9728 OAuth discovery), A2A (task lifecycle, SSE streaming, multi-turn input-required flows), BYOK architecture, multi-tenant RAG isolation

Agentic Systems

AI SDLC harnesses · bounded multi-agent orchestration · LangGraph stateful workflows · LiteLLM multi-provider routing · durable Redis event queues · explicit approval gates · session and durable memory · n8n workflow automation

Product & Developer Interfaces

Node.js · JavaScript · TypeScript · React 19 · REST APIs · GitHub webhooks · CI/CD · developer workflow surfaces

LLM Integration

Anthropic Claude · OpenAI API · Google Gemini · Groq · Ollama · OpenRouter · multi-model fallback · token cost optimization · structured output · prompt engineering · evaluation harnesses

RAG & Knowledge

ChromaDB, Pinecone, pgvector, FAISS, Neo4j · GraphRAG · embedding optimization · chunking strategies · contextual retrieval · semantic caching (Redis)

Backend Foundation

Python (FastAPI, Pydantic) · Java 17 (Spring Boot 3, Spring Cloud) · Go · PostgreSQL · Redis · Kafka · event-driven architecture · microservices

Infrastructure

Docker · Kubernetes · Oracle Cloud Infrastructure (ARM VPS) · Proxmox homelab · AWS (EC2, RDS, S3, EKS) · Terraform · Ansible · GitHub Actions CI/CD · nginx · Cloudflare

Observability

Prometheus · Grafana · OpenTelemetry · cAdvisor · audit trails · GDPR compliance (right to erasure, data export, retention automation)

Certifications

Neo4j Certified Professional · 10× Anthropic (Claude Code in Action, Building with the Claude API, Claude in Amazon Bedrock, Claude with Vertex AI, Subagents, Agent Skills, and more)

03 — PROJECTS

Selected AI Engineering Work

012026 — Present

Personal Multi-Agent Development Platform

Self-hosted platform for AI-assisted software delivery and local infrastructure operations. It coordinates bounded specialist agents and tool-driven workflows across multiple LLM providers, preserves session plus durable local-first memory, and keeps external or destructive actions behind explicit operator confirmation. A Node.js, TypeScript, and React operations surface makes infrastructure, agent activity, scheduled automation, and evidence-backed delivery records observable.

Multi-Agent SystemsLLM RoutingNode.jsTypeScriptReactPythonLocal-First MemoryDocker
02Dec 2025 — Present

Multi-Agent AI SDLC Orchestration Platform

GitHub automation powered by specialized LangGraph agents over per-user ChromaDB knowledge bases. Stateful workflow graphs, durable Redis event queues, human approval gates, GDPR data workflows, and Prometheus/Grafana observability make the delivery harness reliable across restarts.

LangGraphFastAPIChromaDBRedisPostgreSQLPrometheus/GrafanaGitHub Actions
03Feb 2026 — Present

Multi-Protocol AI Agent System (MCP + A2A)

Clinical prior-authorization AI running three interoperability protocols together — SMART on FHIR for data access, MCP for LLM tool interfaces, and A2A for inter-agent delegation. Custom MCP HTTP server with 8 tools, connectable directly from Claude.ai; full task lifecycle with SSE streaming and multi-turn flows.

FastAPIMCP Streamable HTTPA2A ProtocolFHIR R4SSEOpenRouterDocker
04Sep 2024 — Present

AI-Powered Trip Cost Platform

Production trip-cost calculator with a LangGraph route-planning agent — natural-language route creation and modification against the live map — plus shareable trip receipts with server-injected Open Graph previews. Multi-provider routing (Mapbox with OSRM fallback), seasonal glassmorphism design system, Spring Boot single-JAR deploy.

ReactTypeScriptSpring Boot 3LangGraphMapbox GLRedisPostgreSQLDocker
05Apr 2024 — Present

Production n8n Automation Platform

Self-hosted n8n in queue mode on Oracle Cloud Infrastructure, backed by PostgreSQL and Redis. Powers Telegram bots, agentic AI workflows across OpenAI/Claude/Groq, custom MCP servers, and cross-service automation across active projects.

n8nPostgreSQLRedisOracle Cloud InfrastructureDockerMCP
06Jul 2025

Banking REST API in Go

Account management and money transfer API with ACID-compliant transactions and deadlock-safe concurrent transfers. Type-safe database layer generated with SQLC, PASETO token authentication, 96% test coverage, deployed on AWS EKS through CI/CD.

GoPostgreSQLSQLCPASETODockerAWS EKSGitHub Actions
07Feb 2025 — Present

RAG Automotive Diagnostics Assistant

RAG pipeline indexing technical PDF manuals in Pinecone with Ollama embeddings. A Telegram bot fronts it with LangChain for natural-language diagnostic queries, with self-hosted LLM support for offline operation.

RAGLangChainPineconeOllamaTelegram Bot APIPython

04 — CONTACT

Let's Talk

Interested in AI SDLC, agentic platforms, or developer tooling? Drop a message — I read everything.

Based in Ukraine. Available for remote contracts, consulting, and full-time roles. Response time: 24–48h.