Bengaluru, India
Eeshan GuptaSenior AI Engineer — GenAI, RAG & Voice AI Systems
I build the parts of AI products that have to hold up in production — retrieval pipelines, LLM evaluation harnesses, and voice/ASR systems — for pharma, legal, logistics, and customer-support teams at enterprise scale.
Document authoring time — before / after
Authoring speed
GenAI document drafting platform for a top pharmaceutical client
Latency cut
Large-scale NLP extraction and ElasticSearch retrieval pipelines
Tickets deflected
RAG-based product Q&A and onboarding for a travel company
Review speed
NLP relevance & classification pipeline for legal e-discovery
Experience
Eight years building AI that has to work the first time
From regulated pharma document generation to real-time speech pipelines — production systems, not demos.
- Shipped a trigger-based call-summarization plugin on GPT models, automating post-call review for customer-facing teams.
- Built a production speech-to-text plugin for real-time call transcription using Whisper and ElevenLabs ASR.
- Benchmarked STT/ASR providers — OpenAI, ElevenLabs, Google — on accuracy, latency, and cost to guide production vendor decisions.
- Designed an LLM-driven packaging recommendation system for a logistics client, improving cost efficiency at scale.
- Built a RAG-based customer support system for a travel company, cutting support ticket volume by up to 50%.
- Evaluated agent frameworks (Crew.ai, Agno) to orchestrate autonomous data-analysis pipelines.
- Architected a GenAI document-drafting platform for a top pharmaceutical client — 5x faster authoring, no technical skills required to operate.
- Built an AI-assisted patent drafting tool that cut authoring time 3x and sped up IP filing cycles.
- Delivered a large-scale NLP extraction pipeline that reduced manual codification effort by 90%.
- Shipped semantic search and RAG across legal, sales, and marketing repositories, cutting analyst research time significantly.
- Engineered CAAL, an NLP relevance and classification pipeline for legal e-discovery — 10x faster document processing.
- Built custom ElasticSearch plugins that cut retrieval latency 90% for teams reviewing millions of documents.
- Designed a reusable plugin framework that halved future build time for the engineering team.
Earlier: Java Developer, P Cube IT Services (2018)
Selected projects
Independent research and builds
Where I test ideas that are too early — or too weird — for a client roadmap.
MSc thesis · LJMU 2025
Adaptive Personalized Reflective RAG
A LangGraph-orchestrated multi-agent system combining Adaptive-RAG, SELF-RAG, and PersonaRAG
- Query-routing engine that picks retrieval strategy by question complexity — 88.6% classification accuracy.
- Self-critiquing generation via SELF-RAG reflection tokens — 8–15% accuracy gain over standard RAG.
- Context-personalized responses via PersonaRAG, cutting latency 33% and reasoning steps 19%.
Active development
GraphRAG Movie Intelligence Chatbot
Hybrid knowledge-graph + RAG conversational AI over the IMDB dataset
- Combines a relational database, a knowledge graph, and GraphRAG to answer relationship-rich questions vector search alone can't handle.
- Multi-tool LangGraph agent with swappable LLM backends — OpenAI or open-source, model-agnostic.
- Live web search as a knowledge layer, extending past the static dataset in real time.
Latest writing · 24 Oct 2026
I said GraphRAG beats vector RAG. Then I measured it.
When a graph retriever and a tuned hybrid retriever get the same context budget, how much of the graph advantage is left?
Read the article →Toolkit
What I build with
GenAI & LLM
ML & NLP
MLOps & Infra
Data & Backend
Outside the day job
Projects and collaborations
I occasionally take on a small, focused project, usually evaluating or hardening a RAG or voice AI system.
LLM & voice model evaluation
Comparing LLMs, ASR, and RAG pipelines on real data: accuracy, latency, and cost, and a clear answer on which one holds up.
Compare notesHardening a private RAG system
Single-tenant retrieval running inside a company's own AWS or Azure environment, with role-based access and audit logging from the start.
Compare notes