Parshva Gang — AI Researcher

I’m an AI Engineer focused on building end-to-end LLM-powered systems, with hands-on experience designing and implementing retrieval-augmented generation (RAG) pipelines and natural language–to–SQL chatbots. My work centers on improving retrieval quality and system reliability through semantic-aware chunking, vector databases, and metadata-driven search. I’ve built and deployed LLM-based applications in controlled and on-premise environments, enabling secure semantic search over internal document collections and structured data sources. On the system side, I have experience orchestrating multi-stage LLM workflows for tasks such as query understanding, intent modeling, SQL generation, execution, and result summarization. I’ve also implemented intelligent fallback mechanisms to route non-database queries to external knowledge sources when structured data access is not applicable. In addition to AI system development, I have a strong foundation in modern web and backend technologies. I’ve built full-stack and API-driven applications using TypeScript, Node.js, Express, React, and have hands-on experience working with MongoDB and PostgreSQL. This background allows me to design and integrate LLM systems into real-world applications, handling authentication, data persistence, API design, and frontend interaction. I primarily work with Python and have hands-on experience using LangChain, Redis, RabbitMQ, FAISS/ChromaDB, and SQL/NoSQL databases to build backend systems. I’m particularly interested in LLM system design, retrieval evaluation, and bridging the gap between proof-of-concept models and production-ready architectures. I also have a research background, with work published at WWW RelWeb 2025, and I’m actively looking to expand my knowledge.

Stackforce AI infers this person is a Backend-heavy Fullstack developer in the SaaS and Healthcare industries.

Location: Delhi, India

Experience: 9 mos