HEY THERE !

I AM NIKHIL
KUMAR JHA

GenAI Engineer & LLM Architect

SEE MY WORK
Nikhil Kumar Jha
3+
Years Experience
95%
Efficiency Boost
10+
AI Projects

Who Am I?

GenAI Engineer with 3+ years of experience designing, optimizing, and deploying production-grade Generative AI and Agentic AI systems. I specialize in building intelligent automation solutions that transform business operations.

My expertise spans LLMs, RAG pipelines, multi-agent orchestration, fine-tuning (LoRA/QLoRA), quantization, and inference optimization. I've successfully delivered projects that reduced manual processing time from 3 days to under 4 hours and decreased operational effort by 95%.

At Tata Consultancy Services, I architect end-to-end AI solutions using cutting-edge technologies like LangGraph, LangChain, Model Context Protocol, and various vector databases. My work involves everything from prompt engineering to deploying containerized AI services on GCP.

I'm passionate about pushing the boundaries of what's possible with AI, creating systems that not only automate tasks but fundamentally reimagine how work gets done. Multiple "Star Employee" awards recognize my commitment to innovation and business impact.

Core Skills

🤖

Generative AI & LLMs

LLMs Transformers RAG Fine-tuning LoRA/QLoRA Quantization OpenAI API Gemini API
🔗

Agentic AI Systems

LangGraph LangChain MCP Multi-Agent AutoGen CrewAI State Management
⚙️

Backend Engineering

Python FastAPI REST APIs Microservices SQL Async Programming
☁️

MLOps & Cloud

GCP Docker Kubernetes CI/CD LangSmith Monitoring

Professional Experience

AI / GenAI Engineer

Tata Consultancy Services (TCS) | Aug 2022 - Present

  • Designed and implemented multi-agent AI workflows using LangGraph and Model Context Protocol to automate complex enterprise change-control processes
  • Built RAG-based GenAI chatbots using FastAPI, vector databases, and hybrid search for accurate question-answering from enterprise documents
  • Performed LLM fine-tuning using LoRA and QLoRA on LLaMA models, reducing inference memory usage by 40%
  • Deployed containerized AI services using Docker and GCP Cloud Run with CI/CD pipelines
  • Reduced manual processing time from 3 days to under 4 hours per cycle
  • Decreased operational effort by 95% in automation-heavy workflows
  • Recognized with multiple "Star Employee" awards for innovation and business impact

Key Projects

🚀 Multi-Agent Control System

Agentic AI | LangGraph | MCP | RAG

  • Designed state-aware autonomous agent to answer 200+ regulatory questions
  • Implemented Model Context Protocol for structured context exchange
  • Achieved 95% reduction in manual question-answering

📚 Knowledge Assistant

RAG | LLMs | Vector Search

  • Built scalable RAG pipeline with Pinecone and hybrid search
  • Integrated semantic and keyword search for accuracy
  • Reduced HR support ticket volume by 60%

✅ Compliance Platform

NLP | Classification | HITL

  • Developed NLP-based classification engine
  • Built human-in-the-loop validation with FastAPI
  • Improved categorization accuracy by 32%

Let's Work Together

Interested in building the future with AI? Let's connect!

GET IN TOUCH