I’m an engineer who enjoys solving difficult problems, figuring out how things should be built, and making systems work at scale. Over the years, I’ve worked on distributed systems handling hundreds of millions of requests per minute and processing millions of transactions in under a minute. A lot of my work has been around building highly available systems, improving performance and latency, and solving the kind of problems that come with operating systems at scale. In recent years, I’ve also been spending a lot of time working with Generative AI, LLM applications and AI agents. I’m particularly interested in the engineering side of AI, designing the right architecture, building RAG and agentic systems, and figuring out how to evaluate and monitor AI applications in production. I enjoy going beyond just making something work. I like understanding why it works, where it can fail, and how we can build it in a way that is reliable and scalable. I’ve also led engineering teams and worked closely with product managers, founders and customers, so I enjoy both the technical and people side of building products. Happy to share what I’ve learned with engineers and founders who are working on AI products, distributed systems, architecture, or simply trying to solve a challenging technical problem.