Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Software Engineer with around 5 years of experience specializing in AI/Generative AI, RAG systems, and cloud-native microservices architecture. Strong expertise in Java, Spring Boot, and distributed systems design with experience building LLM-powered applications and agentic AI systems. Skilled in developing and deploying scalable systems on AWS using Kubernetes, Docker, and Terraform, with focus on low-latency APIs and observability. Expertise in integrating LLMs, prompt engineering, and semantic search to deliver enterprise GenAI copilots and automation solutions.…Software Engineer with around 5 years of experience specializing in AI/Generative AI, RAG systems, and cloud-native microservices architecture. Strong expertise in Java, Spring Boot, and distributed systems design with experience building LLM-powered applications and agentic AI systems. Skilled in developing and deploying scalable systems on AWS using Kubernetes, Docker, and Terraform, with focus on low-latency APIs and observability. Expertise in integrating LLMs, prompt engineering, and semantic search to deliver enterprise GenAI copilots and automation solutions.

Naveen Chava

Software Engineer, AI Developer, AI Engineer, +2





Software Engineer with around 5 years of experience specializing in AI/Generative AI, RAG systems, and cloud-native microservices architecture. Strong expertise in Java, Spring Boot, and distributed systems design with experience building LLM-powered applications and agentic AI systems. Skilled in developing and deploying scalable systems on AWS using Kubernetes, Docker, and Terraform, with focus on low-latency APIs and observability. Expertise in integrating LLMs, prompt engineering, and semantic search to deliver enterprise GenAI copilots and automation solutions.…Software Engineer with around 5 years of experience specializing in AI/Generative AI, RAG systems, and cloud-native microservices architecture. Strong expertise in Java, Spring Boot, and distributed systems design with experience building LLM-powered applications and agentic AI systems. Skilled in developing and deploying scalable systems on AWS using Kubernetes, Docker, and Terraform, with focus on low-latency APIs and observability. Expertise in integrating LLMs, prompt engineering, and semantic search to deliver enterprise GenAI copilots and automation solutions.

Available to hire

Software Engineer with around 5 years of experience specializing in AI/Generative AI, RAG systems, and cloud-native microservices architecture. Strong expertise in Java, Spring Boot, and distributed systems design with experience building LLM-powered applications and agentic AI systems.

Skilled in developing and deploying scalable systems on AWS using Kubernetes, Docker, and Terraform, with focus on low-latency APIs and observability. Expertise in integrating LLMs, prompt engineering, and semantic search to deliver enterprise GenAI copilots and automation solutions.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Work Experience

Software Engineer at Paypal

May 1, 2025 - Present

Designed and deployed a GenAI-powered customer support copilot using LangChain-based RAG pipelines, integrating LLMs with internal knowledge bases to generate context-aware responses and reduce average ticket resolution time by 38%. Engineered backend services using Java, Spring Boot, and Hibernate, exposing REST and GraphQL APIs for real-time query handling and AI inference orchestration, supporting 10K+ concurrent support sessions with <200ms latency. Built a semantic retrieval layer using FAISS and MongoDB Atlas Vector Search to improve Top-3 retrieval accuracy from 61% to 84% and enable low-latency RAG responses. Developed LLM-based summarization pipelines for disputes and payment histories, reducing manual review effort by 3.2 hours per agent per day and increasing case throughput by 1.6x. Containerized microservices and deployed on Kubernetes (EKS) with Terraform-based IaC and automated CI/CD (GitHub Actions), reducing deployment time by 50%. Implemented observability using Prome

Software Engineer at LTIMindtree

October 1, 2019 - July 31, 2023

Designed a cloud-native core banking microservices architecture using Java, Spring Boot, and Node.js, integrating SAP S/4HANA via REST APIs for real-time transaction processing with <250ms API latency at 5K+ TPS. Built a secure API gateway layer (Spring Cloud Gateway + OAuth2 + JWT) for account and payment services enforcing zero-trust authentication and role-based access control across 120+ banking APIs. Developed event-driven data pipelines using Kafka and PostgreSQL for real-time synchronization between core banking, CRM, and SAP modules, processing 60k+ daily financial events with near real-time consistency. Engineered microservices using domain-driven design (DDD) to reduce coupling and improve scalability, achieving 99.95% system availability. Implemented CI/CD pipelines (Jenkins, GitHub Actions), containerizing with Docker and deploying to AWS EKS with automated rollback, reducing deployment cycles from 3 days to under 2 hours. Collaborated on an Angular-based banking dashboard