04 //
Building scalable distributed systems and intelligent AI-powered applications — from RAG pipelines to high-throughput microservices.
I'm a Backend Engineer with 3 years of experience designing and shipping scalable, distributed systems. My work spans cloud-native microservices, real-time data pipelines, and observability infrastructure.
Recently, I've been deep in the AI application layer — building RAG pipelines, embedding systems, and semantic search powered by LLMs. I'm drawn to the intersection of reliable backend engineering and intelligent automation.
I hold certifications in Google Cloud (ACE) and Oracle Cloud AI (OCI Generative AI), and I'm particularly passionate about making production AI systems observable, robust, and fast.
A full Retrieval-Augmented Generation pipeline for semantic document search and question answering. Implements document chunking, embedding generation, and vector storage with FAISS — with LLM-based response generation via prompt engineering.
High-throughput trading platform with real-time market data via Redis caching and WebSocket. Features order matching, portfolio management, and risk assessment modules — deployed on AWS ECS with Spring Boot microservices and RDS persistence.
Real-time multiplayer browser game with WebSocket-synchronized player movement and state across clients. Designed a scalable game architecture supporting multiple players, movement constraints, and boundary enforcement — hosted on AWS ECS with VPC networking and load balancing.
Whether it's a backend challenge, an AI systems project, or just a conversation — I'm always open.
