> init --user
I build production-grade LLM systems, agentic infrastructure, and real-time AI that drive measurable impact on automation and user engagement.
Riverside, CA
> ls ./projects/ — recent shipped work
> project_01
Production-grade agentic RAG system using LangChain and Postgres vector search. Translates natural language into SQL for real-time customer analytics — built and shipped at Beehive AI.
> project_02
Architected a multi-agent commerce system on Vertex AI + LangGraph with semantic search, dynamic UI, and conversational interfaces for personalized product recommendations.
> project_03
Data categorization framework that validates and refines category labels using LLM-driven evaluation — drove 80% automation and reduced manual labeling effort.
> project_04
Scalable persona simulation framework using LLMs, contextual retrieval, and memory systems to model user behavior and inform product decisions.
> project_05
Self-supervised audio embedding model trained on 35K+ hours of audio. Reached 86% downstream accuracy and beat BERT-based text-only baselines by 5 points (work at Deepgram).
> project_06
LLM-based pipeline assessing medical research paper quality. GPT-4 hit 75% eval accuracy via prompt optimization; Mixtral reached 69% via QLoRA fine-tuning (PI School fellowship).
> cat ./posts/* — notes from building real AI systems
The first step every LLM takes — implemented from scratch. Before a Transformer can process text, it has to be turned into numbers.
The mathematical foundations of generative modeling — divergence measures, latent variable models, and the theory behind GANs and diffusion models.
> more posts shipping soon — say hi via Get in Touch below.
> git log --all --oneline
> Jul 2024 — Present
Engineered an agentic RAG system (LangChain + Postgres pgvector) for natural-language → SQL analytics. Built an LLM-powered QA framework reaching 80% automation, a virtual persona simulation framework, and architected a multi-agent commerce system on Vertex AI + LangGraph.
> Jan 2024 — Jul 2024
Shipped an LSTM-based sequential prediction model for long-term content performance. Led a comment ranking system using semantic embeddings + LLM summaries that lifted CTR by 4.5% and comment volume by 4.0%.
> Dec 2023 — Feb 2024
Automated reliability assessment of medical research papers using LLM-based algorithms. Improved GPT-4 evaluation accuracy to 75% via prompt optimization and pushed Mixtral to 69% with QLoRA fine-tuning.
> Jun 2023 — Sep 2023
Trained a self-supervised audio embedding model on 35K+ hours of audio (86% downstream accuracy). Engineered a multimodal embedding space aligning audio and text, beating text-only baselines by 5 points.
> cat ./about.md
I’m Kuntal — an AI engineer working on LLM systems, retrieval pipelines, and multi-agent infrastructure. I like turning messy, ambiguous problems into clean, production-shaped products.
Right now I’m at Beehive AI, where I build agentic RAG systems, LLM-powered evaluation frameworks, and virtual persona simulators that help product teams make sharper decisions.
Before that, I spent seven years doing theoretical and computational particle physics for my Ph.D. at UC Riverside, with valuable research experiences at Deepgram (multimodal audio embeddings), PI School in Rome (LLM evaluation for medical research), and Pocket FM (sequential prediction + comment ranking).
University of California, Riverside
Ph.D., Physics
Sep 2017 — Jun 2024
Indian Institute of Science Education and Research, Kolkata
BS-MS Dual Degree, Physics
Aug 2012 — May 2017
> ls -la ./stack/ — tools I reach for most often
> open inbox — reply latency: low
My inbox is always open — whether you have a project in mind, a research collaboration, or just want to say hi, I’ll do my best to reply.
Say Hello> kuntal.beehiveai@gmail.com · +1 (951) 202-8635