Open to opportunities

Vivek Tiwari

@vivektiwari1

Message

Data Scientist with expertise in AI and backend engineering.

India

Message

What I'm looking for

I am seeking a role that fosters innovation and collaboration, with opportunities for growth in AI and backend technologies.

I am a passionate Data Scientist currently working at IBM, where I contribute to the development of modular, enterprise-grade Hybrid RAG systems tailored for the financial domain. My work involves leveraging advanced technologies such as vector search and knowledge graphs to enhance the accuracy and reliability of our solutions. I take pride in building and maintaining ingestion and preprocessing pipelines for multi-layout, semi-structured documents, optimizing for chunking efficiency and retrieval relevance.

Previously, I served as a Lead Backend Engineer at Tata Consultancy Services, where I led a team to create an internal GenAI chatbot that significantly improved technical query responses for over 40 developer teams. My experience includes designing scalable APIs and implementing intelligent caching mechanisms that drastically reduced query latency. I am also actively involved in innovative projects like Woodle.ai and RiotJet.com, which showcase my ability to blend AI with practical applications.

Experience

Work history, roles, and key accomplishments

Current

Data Scientist

Current

IBM

Aug 2024 - Present (9 months)

Contributed to the development of modular, enterprise-grade Hybrid RAG systems for financial domain use cases, leveraging vector search, knowledge graphs, and fallback strategies to improve accuracy and reliability. Built and maintained ingestion and preprocessing pipelines for multi-layout, semi-structured documents, optimizing for chunking efficiency, embedding quality, and retrieval relevance.

Hybrid RAG Vector Search Knowledge Graphs Data Ingestion LLM Context Fit Docker Kubernetes

Lead Backend Engineer

Tata Consultancy Services

Jun 2021 - Aug 2024 (3 years 2 months)

Led a backend team to build an internal GenAI chatbot that answered technical queries for 40+ developer teams across the organization. Designed scalable APIs and integrated vector search to support low-latency responses, achieving peak throughput of 72,000+ requests per hour with high availability.

Backend Development Vector Search Python AWS