{"name":"Ruslan Shulga","headline":"VP Engineering, AI Platform","location":"New York, NY","bio":"VP Engineering at JPMorgan Chase. I lead the AI platform team behind our multi-agent orchestration and hybrid retrieval, plus the custom MCP servers several thousand employees use every day. This site is where a team of AI agents shows what it can ship on its own.","links":[{"label":"Email","href":"mailto:nycruslan@gmail.com"},{"label":"LinkedIn","href":"https://www.linkedin.com/in/nycruslan/"},{"label":"GitHub","href":"https://github.com/nycruslan"}],"experience":[{"company":"JPMorgan Chase & Co.","title":"Vice President, Senior Software Engineer Lead – AI Platforms & Systems","period":"Sep 2021 — Present","summary":"Built the multi-agent workflows several thousand employees use firm-wide, on LangGraph with the Claude Agent SDK and OpenAI Agents SDK, and cut manual processing on the flagship workflow by about 55%. Built a model-agnostic AI gateway over AWS Bedrock, Azure OpenAI and the Anthropic API that around 8 product teams route through, a hybrid retrieval pipeline that lifted precision roughly 35%, and the MCP servers that turned sprint-long AI features into a day or two. Lead a team of 7 across AI research, backend and platform."},{"company":"Earth Designs","title":"Full Stack Web Developer","period":"Apr 2020 — Sep 2021","summary":"Ran the React and Next.js migration across several production apps, from design through deployment. Built a reusable component library, set up performance monitoring, and mentored two junior engineers."},{"company":"PPS Capital","title":"Information Technology Manager","period":"Jan 2018 — Apr 2020","summary":"Ran IT operations and infrastructure strategy company-wide, and led internal web apps for analytics and reporting. Set up disaster recovery and cybersecurity practices that protected client data."},{"company":"Earth Designs","title":"Technology Manager","period":"Feb 2016 — Jan 2018","summary":"Led API-driven web platforms and microservices, worked closely with the CEO on tech strategy, and set up the team's documentation and onboarding."}],"projects":[{"name":"Theseus","description":"This portfolio. An autonomous team of AI agents keeps rebuilding it, sprint by sprint, in public.","href":"https://github.com/nycruslan/theseus-portfolio"},{"name":"view-json-react","description":"An accessible, dependency-free React JSON tree viewer with safe inspection, search and virtualization. Open source.","href":"https://github.com/nycruslan/view-json-react"}],"education":[{"school":"Harvard University","credential":"Certificate in Computer Science (CS50)","period":"Jun 2020 — Dec 2020"},{"school":"Kyiv National Economic University","credential":"Bachelor's and Master's, International Economics","period":"Sep 2010 — Jul 2015"}],"stack":["Python","TypeScript","LangGraph","LangChain","Claude Agent SDK","OpenAI Agents SDK","MCP","Pinecone","Weaviate","pgvector","AWS Bedrock","Azure OpenAI","React","Next.js","Astro","Node.js","Docker","Kubernetes"],"email":"nycruslan@gmail.com","caseStudies":[{"slug":"multi-agent-platform","title":"Multi-agent orchestration platform","summary":"Production multi-agent workflows used by several thousand employees firm-wide. LangGraph orchestrates Claude Agent SDK and OpenAI Agents SDK. Each agent has persistent memory and calls internal tools. Irreversible actions pause for a human checkpoint.","results":[{"label":"Manual processing cut on the flagship workflow","value":"~55%"},{"label":"Employees using it firm-wide","value":"Several thousand"}],"stack":["LangGraph","Claude Agent SDK","OpenAI Agents SDK","Python","React"],"url":"https://portfolio.ruslanshulga.com/work/multi-agent-platform"},{"slug":"hybrid-rag","title":"Hybrid retrieval pipeline","summary":"Replaced an embedding-only RAG with a hybrid pipeline: dense plus sparse retrieval, cross-encoder re-ranking, indexed across Pinecone, Weaviate and pgvector depending on the use case. The pieces that mattered weren't the models. They were the eval harness and the index strategy per domain.","results":[{"label":"Retrieval precision improvement","value":"~35%"},{"label":"Eval cadence","value":"Nightly"}],"stack":["Pinecone","Weaviate","pgvector","Cross-encoder re-ranking","RAGAS"],"url":"https://portfolio.ruslanshulga.com/work/hybrid-rag"},{"slug":"mcp-servers","title":"Internal MCP servers","summary":"Custom Model Context Protocol servers that connect Claude to internal APIs and databases. Features that used to take a sprint now take a day or two.","results":[{"label":"Typical feature ship time","value":"1-2 days vs 1 sprint"}],"stack":["MCP","Python","Anthropic API","Internal APIs"],"url":"https://portfolio.ruslanshulga.com/work/mcp-servers"},{"slug":"ai-gateway","title":"Model-agnostic AI gateway","summary":"An AI gateway on top of AWS Bedrock and Azure OpenAI, with direct Anthropic API access for newer Claude models. Around 8 product teams route through it for model selection and automatic failover, with cost tracked per team across Claude, GPT-4, Llama and Titan.","results":[{"label":"Product teams routing through","value":"~8"},{"label":"Providers supported","value":"3 primary, 4+ models"}],"stack":["AWS Bedrock","Azure OpenAI","Anthropic API","Cost tracking","Provider failover"],"url":"https://portfolio.ruslanshulga.com/work/ai-gateway"},{"slug":"document-ai","title":"Multimodal document pipelines","summary":"Document and image processing pipelines on Claude Vision and GPT-4V, with Gemini added recently for cost reasons. Handles the first pass of compliance reviews that used to sit with analysts.","results":[{"label":"Use case","value":"First-pass compliance review"},{"label":"Originally done by","value":"Human analysts"}],"stack":["Claude Vision","GPT-4V","Gemini","OCR","Compliance review automation"],"url":"https://portfolio.ruslanshulga.com/work/document-ai"}],"machineReadable":{"mcp":"https://portfolio.ruslanshulga.com/api/mcp","llmsTxt":"https://portfolio.ruslanshulga.com/llms.txt","evals":"https://portfolio.ruslanshulga.com/evals"}}