About
I design and build scalable AI infrastructure used by engineering teams at enterprise scale.
Most recently, I led development of a multi-cloud AI Gateway enabling 100+ teams to securely access large language models across AWS, Azure, and GCP — processing over 1B tokens per day with built-in governance, resiliency, and cost controls.
Tech Stack
I have experience across various aspects of full-stack development. In my past roles, I worked on event-driven microservices built with TypeScript and AWS Lambda.
In my current role, I work extensively with LLM APIs, creating example applications and demonstrating how to integrate agentic RAG techniques into real-world use cases.
My work focuses on: • Distributed systems and platform architecture • Enterprise AI access and governance • Reliability, observability, and cost optimization • Standardizing infrastructure for cross-team adoption
I’m particularly interested in building internal platforms that simplify complexity and create long-term leverage for engineering organizations.
Technical Focus
I work primarily at the intersection of AI systems and cloud-native infrastructure.
AI & LLM Systems
- LLM APIs (OpenAI, Anthropic, Bedrock)
- LangChain and agentic RAG architectures
- Prompt orchestration and retrieval pipelines
Cloud & Infrastructure
- AWS Serverless (Lambda, API Gateway, Step Functions)
- Infrastructure as Code (AWS CDK)
- Multi-cloud LLM routing and governance
Observability & Data
- Datadog monitoring and telemetry
- NoSQL systems (DynamoDB)
- Event-driven architectures
Application Layer
- TypeScript / Node.js
- React
You can reach out to me via email.