Backend Engineer building production-oriented APIs, AI-integrated systems, Retrieval-Augmented Generation pipelines, and secure authentication architectures using Python, FastAPI, PostgreSQL, Redis, Qdrant, and OpenAI APIs.
I'm a Computer Science graduate from Sathyabama Institute of Science and Technology (B.E. CSE, CGPA: 7.96/10) and a Backend Engineer focused on building reliable backend systems, AI-powered applications, and scalable APIs.
My interests include distributed systems, Retrieval-Augmented Generation (RAG), asynchronous processing, secure authentication architectures, and production-ready backend design. I enjoy designing systems that prioritize maintainability, reliability, observability, and performance while solving real-world engineering problems.
I prefer understanding the underlying architecture of systems rather than relying solely on abstractions. My focus is on building practical solutions with strong engineering fundamentals — prioritizing reliability, observability, and maintainability over surface-level complexity.
Contributing to backend services and API development supporting AI-powered workflows and platform features.
Built AI-assisted debugging platform using Kafka, Qdrant, Redis, and OpenAI — combining async ingestion pipelines with RAG-based root cause analysis.
Designed secure authentication systems with JWT refresh token rotation, reuse detection, RBAC, and Redis-backed rate limiting and token blacklisting.
Developed and deployed production FastAPI applications with PostgreSQL, Redis, and cloud infrastructure on Render, Vercel, and Upstash.
Built semantic retrieval systems using OpenAI embeddings, Qdrant vector search, metadata filtering, and context-aware response generation.
Implemented Kafka-driven asynchronous event processing workflows with fault-tolerant retry mechanisms and structured observability logging.
A production-style AI backend system designed to help developers investigate incidents, failures, and debugging scenarios across distributed systems using Retrieval-Augmented Generation (RAG) and LLM-powered root cause analysis.
A production-oriented full-stack backend system demonstrating secure authentication, Redis-based security controls, inventory management, cart workflows, and scalable API architecture. Backend is the primary focus; React frontend serves as a client interface.
A production-ready FastAPI backend for financial data processing with role-based access control and real-time dashboard analytics. Demonstrates clean modular architecture, secure authentication, and scalable data handling.
An end-to-end machine learning system for predicting cardiac risk using ensemble learning techniques, built on an IEEE research implementation with ~3,200+ clinical records. Implementation aligned with IEEE-published research on hybrid ML models for cardiac risk prediction.
Backend Engineer | AI Systems Developer | Python, FastAPI, PostgreSQL, Redis, Kafka | RAG Pipelines, LLMs, Vector Search
Open to the following roles: