Prabhat
Senior AI Engineer. LLM Systems Builder
Senior AI Engineer with 6.5+ years of experience building LLM-powered products, RAG systems, and agentic AI platforms from ground up. Currently driving hybrid search, knowledge orchestration, and VLM-based systems at AI71 (Abu Dhabi).
Prabhat Kumar Gupta

Work Experience

6.5+ years building LLM systems, RAG & agentic AI

1.2 years ยท Abu Dhabi, UAE

Sr. AI Engineer ยท AI71

  • Joined as 2nd AI Engineer; contributed to core architecture, ML system planning, RAG pipelines, metrics & evaluation.
  • Designed Vector & Hybrid Search pipelines for large-scale document retrieval and semantic ranking.
  • Built scalable Knowledge Base & Ingestion Framework for 7+ doc types (PDF, PPTX, DOCX, XLSX, CSV, MD, JSON).
  • Optimized retriever API: 5s โ†’ 2s latency (60% faster).
  • Built ReAct-based Agentic Orchestrator for multi-agent workflows; 5x use-case coverage.
  • Engineered RAG, fine-tuning & benchmarking with Precision@k, Recall@k, answer-correctness, faithfulness.
0.5 years ยท Bangalore, India

Senior ML Engineer ยท Zepto

  • Extensible ML model serving platform with TF-Serving; latency 400ms โ†’ 5ms (99% reduction).
  • VLM to auto-generate product filters; advanced search on 10k+ products with GPT-4o.
  • Model-lifecycle pipeline: no-code Training, Evaluation & Deployment on Databricks.
  • MLFlow registry with 100% model artifacts & metadata registration.
4.7 years ยท Gurgaon, India

Lead Product Engineer ยท Sprinklr

  • Fine-tuned Llama3-8B-Instruct for banking chatbot; 90%+ accuracy in native JSON matching.
  • LLM Chatbot as personal WhatsApp agent; Text-to-SQL AI Copilot for Salesforce DB (95% faster query creation).
  • Agent Scoring with distilBERT (NER & classification); 100% product revenue growth in 2 years.
  • Secured 4000+ ML deployments & 300+ Docker images with IAM and compliance migrations.
  • Kafka pipeline optimization: 70% fewer false alerts; 100% autoscaler reliability via custom K8s Operator.
  • K8s cluster of 9 GPU nodes with volume mounts, RBACs & UI for training and monitoring.
  • Internal Filesystem API across AWS, Azure, GCP & local systems powering 90% of live deployments.

Recommendations & Kudos



Recommendation from Jitendra
Recommendation from Hardik
Recommendation from Vishal

Blogs

Thoughts on agentic AI, LLM systems, and engineering.

> Agentic Patterns in AI Systems

Agentic design patterns implemented from scratch with first-principles in LangGraph. Includes 4 important patterns, 1. Reflection, 2. ReAct Tool-Use, 3. Orchestrator-Worker, 4. Multi-Agent.

~8 min read

> Workflow Patterns in AI Systems

Apart from writing single functions for each task, we can combine function through static workflows and achieve more depth. Three commonly used workflow patterns: 1. Sequential Chaining, 2. Routing, and 3. Parallelization.

~7 min read

Technical Expertise

Agentic AI

ReAct-based Agentic Orchestrator, multi-agent workflows, dynamic workflow management. Increasing use-case coverage by 5x.

LLMs & RAG Systems

GPT-5, Claude-Sonnet-4, BAAI/BGE-m3, DeepSeek-OCR, LoRA, Mistral. Building production RAG pipelines and knowledge orchestration systems.

ML Frameworks

PyTorch, LangChain, LlamaIndex, TensorFlow, Keras, Transformers, Accelerate, DeepSpeed, PEFT.

MLOps & Infrastructure

VLLM, MLC, Docker, Kubernetes, Kafka, GitHub Actions. Building scalable ML infrastructure and deployment pipelines.

Fine-tuning & Evaluation

RAG, fine-tuning, and benchmarking frameworks. Precision@k, Recall@k, answer-correctness, faithfulness metrics.

Cloud Platforms

AWS, Google Cloud, Azure. Deploying and managing ML workloads across multiple cloud providers.
Get in touch

Projects & Articles โœจ

Open-Cursor - Free AI coding assistant

Open-Cursor - Free AI Coding Assistant

An open-source version of Cursor coding agent that runs locally, fully powered with open-source LLMs. Privacy-first, cost-free, and fully customizable AI coding assistant.

Alpha-X time management

Alpha-X

A personal time management and optimization system integrated with Google Sheets and WhatsApp. Tracks goals, sends weekly and monthly insights, and helps monitor progress.

View on GitHub โ†’
Kubernetes - scalable container orchestrator

What is Kubernetes? - A Basic Guide

Learn about the Kubernetes. A container Orchestration tool on a basic level, and how it is making the job of Developers simpler.

Read Blog โ†’
article image

Agentic AI & Multi-Agent Systems

Building ReAct-based agentic orchestrators and multi-agent workflows for dynamic use-case coverage.

Read Blog โ†’