Lakshmi Chakradhar Vijayarao

AI Engineer specializing in LLMs, RAG, & Multi-Agent Systems

About Me

AI Engineer specializing in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Reinforcement Learning (RL), and multi-agent systems. Experienced in building end-to-end production-grade AI pipelines, including LLM fine-tuning (LoRA/QLoRA), dense retrieval (FAISS/ChromaDB), hybrid RAG architectures, verification agents, GPU-optimized inference, and RL-based query optimization.

Skills & Expertise

RAG
LLM Fine-Tuning (LoRA/QLoRA)
LLM Agents & Tool Calling
Hugging Face Transformers
LangChain
SentenceTransformers
Hybrid Retrieval
Vector Stores (FAISS, ChromaDB)
AI Safety & Hallucination Detection
PyTorch
TensorFlow
Scikit-Learn
Reinforcement Learning
MLflow
Docker
CI/CD for ML
FastAPI
AWS SageMaker
Streamlit
PySpark
Airflow
Python
SQL
Java
JavaScript
C++
Git
Linux

Education

The University of Texas at Dallas

Dallas, USA

Master of Science, Computer Science

May 2025

R.M.K Engineering College

Chennai, India

Bachelor of Engineering, Electronics and Communication Engineering

Mar 2023

Featured Projects

MedRAG – Clinical Retrieval-Augmented Assistant

LLMs
RAG
FAISS
FastAPI

Built clinical RAG system using dense + BM25 hybrid retrieval, improving terminology recall +31%. Reduced hallucinations 34% through evidence-grounded generation + multi-agent verification.

FinAgentX – Multi-Agent Financial Analytics System

LLM Agents
Tool Calling
Retrieval
Streamlit

Engineered multi-agent framework for market analysis, risk scoring, and regulatory retrieval. Implemented retrieval-aware routing with compressed FAISS, cutting latency –41%.

SafeRAG – Hallucination Detection & Verification Engine

AI Safety
Verification Agents
Grounding Metrics

Designed multi-stage hallucination detection pipeline with evidence alignment + attribution. Reduced unsupported claims –46% across clinical and financial datasets.

LoRA-ClinicalBERT – Medical LLM Domain Adaptation

LoRA
QLoRA
PEFT
Hugging Face

Fine-tuned LLaMA/Mistral models on PubMed + clinical discharge summaries. Increased ROUGE-L +19% while reducing compute cost 63% using QLoRA.

Certifications

  • Hugging Face Building and Fine-Tuning LLM
  • Microsoft Certified: AI & ML Engineer
  • AWS Certified Cloud Practitioner – AWS Academy

Get In Touch

I'm currently open to new opportunities and collaborations. Feel free to reach out if you have a project in mind, want to discuss AI, or just say hi!