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

Software engineer specializing in research and production systems, building semantic search/RAG assistants, real-time analytics backends, and developer-friendly APIs. Strong focus on retrieval quality, prompt/retrieval evaluation, and measurable latency/throughput improvements. Experience spans React + FastAPI services, microservices, Kafka-based ingestion, and cloud deployments on AWS/Azure/GCP. Skilled in end-to-end system design: indexing pipelines, chunking/embedding workflows, caching, distributed scheduling, and CI/CD automation.…Software engineer specializing in research and production systems, building semantic search/RAG assistants, real-time analytics backends, and developer-friendly APIs. Strong focus on retrieval quality, prompt/retrieval evaluation, and measurable latency/throughput improvements. Experience spans React + FastAPI services, microservices, Kafka-based ingestion, and cloud deployments on AWS/Azure/GCP. Skilled in end-to-end system design: indexing pipelines, chunking/embedding workflows, caching, distributed scheduling, and CI/CD automation.

Nanda Kishore Vuppili

Full Stack Developer, Back-End Developer, Front-End Developer, +2





Software engineer specializing in research and production systems, building semantic search/RAG assistants, real-time analytics backends, and developer-friendly APIs. Strong focus on retrieval quality, prompt/retrieval evaluation, and measurable latency/throughput improvements. Experience spans React + FastAPI services, microservices, Kafka-based ingestion, and cloud deployments on AWS/Azure/GCP. Skilled in end-to-end system design: indexing pipelines, chunking/embedding workflows, caching, distributed scheduling, and CI/CD automation.…Software engineer specializing in research and production systems, building semantic search/RAG assistants, real-time analytics backends, and developer-friendly APIs. Strong focus on retrieval quality, prompt/retrieval evaluation, and measurable latency/throughput improvements. Experience spans React + FastAPI services, microservices, Kafka-based ingestion, and cloud deployments on AWS/Azure/GCP. Skilled in end-to-end system design: indexing pipelines, chunking/embedding workflows, caching, distributed scheduling, and CI/CD automation.

Available to hire

Software engineer specializing in research and production systems, building semantic search/RAG assistants, real-time analytics backends, and developer-friendly APIs. Strong focus on retrieval quality, prompt/retrieval evaluation, and measurable latency/throughput improvements.

Experience spans React + FastAPI services, microservices, Kafka-based ingestion, and cloud deployments on AWS/Azure/GCP. Skilled in end-to-end system design: indexing pipelines, chunking/embedding workflows, caching, distributed scheduling, and CI/CD automation.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Beginner

Beginner

Language

Javanese

Advanced

Work Experience

Software Engineer (Research) at Stony Brook, NY

November 1, 2024 - Present

Built a React + FastAPI research assistant for semantic search and summarization over a 5,000+ document corpus by integrating LangChain, GPT-4, and FAISS. Implemented automated ingestion and chunking pipelines that parse, embed, and index new papers, reducing document-add time from hours to minutes while keeping the search index continuously updated. Developed a RAGAS evaluation harness to track retrieval precision and answer faithfulness, improving faithfulness to 0.90+ and catching quality regressions while tuning prompts and retrieval strategies. Added an MCP-based agentic layer with Redis caching for repeated queries, reducing average query latency by 40% and enabling multi-step retrieve-and-summarize flows within a single conversation.

Software Engineer at Matchday AI

June 1, 2022 - December 31, 2023

Built backend services for a real-time sports analytics platform using Python, Flask, MongoDB, and SQLite, reducing API response latency by 27% for live match reporting workflows. Developed REST APIs consumed by a React dashboard to serve structured match event data, standardizing response schemas and reducing frontend integration time by 35%. Introduced Kafka-based asynchronous messaging to decouple data ingestion from processing, increasing system throughput by 25% during peak event load. Added OAuth 2.0 role-based access, Prometheus/Grafana monitoring, and Azure Pipelines deployment automation, improving service stability and reducing release latency by 38%. Optimized MongoDB access with compound indexing and Redis caching for frequently accessed match data, reducing average query latency by 30% while sustaining live-match traffic during peak loads.

Full Stack Engineer Intern at Phoenix Global Trade Solutions

February 1, 2022 - May 31, 2022

Built Python and Flask backend services exposing REST and gRPC APIs backed by Redis to power a real-time analytics dashboard, improving UI responsiveness by 8% and service reliability by 12%. Integrated Azure Monitor telemetry across dashboard-backed microservices to improve visibility into API performance and detect reliability issues faster.