Technical Lead for AI/ML — I architect the agent frameworks, RAG pipelines and LLM gateways behind AI products running in production.
One connected AI platform, not five separate projects
I build AI systems as one connected platform rather than five disconnected projects: gateways that make models and tools reliably available, a knowledge base that grounds them in real content, an agent framework standing on both, and the chatbots and automation workflows people actually use on top.
A conversational interface end users talk to directly
chat.interfaceMulti-step tasks an agent completes on a trigger, unattended
workflow.autoConfig-driven agents, teams, and multi-step reasoning
agent.frameworkOne governed path to every model provider
llm.gatewayRoutes tools and context to every agent
mcp.gatewayDocuments crawled, chunked, embedded, and indexed for search
knowledge.baseOpenAI, Anthropic and Bedrock behind one interface, swappable per task
modelsEC2, ECS, Kubernetes and Docker — what the whole platform runs on
infraSource data arriving from outside, made retrievable
ingestionThings I've shipped
An agentic AI system built on the Agno framework that analyzes millions of historical support tickets and recommends resolutions in real time.
60% reduction in resolution time, 40% drop in support costs