SDE II ML at Amazon Web Services
I'm a software engineer with a full-stack background and a current focus on machine learning systems. My interests include LLM inference, KV-cache reuse, memory efficiency, and model-serving infrastructure.
Previously, I worked on web applications, microservices, automated testing, and delivery pipelines.
| Applications | Infrastructure | Current interests |
|---|---|---|
| Java · Spring Boot | AWS · Docker | LLM inference & serving |
| React · TypeScript | CI/CD · Jenkins | KV-cache reuse |
| GraphQL · REST APIs | SQL · MongoDB | Memory efficiency |
Amazon Web Services
SDE II ML · May 2026–present
SDE ML · December 2024–April 2026
DBS Bank
Full Stack Developer · September 2020–August 2022
React and TypeScript micro frontends, GraphQL, Spring Boot microservices, testing, and containerized delivery.
NCR Corporation
Full Stack Developer · January–July 2020
A few infrastructure projects I'm exploring through forks:
- LMCache — LLM KV-cache infrastructure.
- External KV service backend — Shared-memory storage and HTTP service integration for LMCache.
MS, Computer Science · California State University San Marcos · 2022–2024
Bachelor's, Computer Science · JNTUH College of Engineering Hyderabad · 2016–2020
Personal profile · Views are my own