Hey!
Software Engineer focused on backend systems, distributed architectures, and high-performance services.
Skilled at designing and building Generative AI features into production systems, including RAG pipelines, embeddings, and intelligent automation.
My background is rooted in enterprise-scale systems. I previously worked as a Member of Technical Staff at VMware (later Broadcom), where I designed and owned core distributed components for the AVI Load Balancer, including the State Cache Manager used in high-availability environments.
More recently, I’ve been working at US startups, applying the same systems rigor to modern backend platforms and Applied AI use cases. I build backend services and infrastructure that integrate Generative AI into production systems like RAG pipelines, multi-LLM workflows, and agent-driven automation while prioritizing reliability and latency.