Dharani Chalichama

Hi, I'm

Dharani Chalichama

I build LLM, RAG, and multi-agent systems that hold up in production, plus the full-stack products around them.

My LinkedIn profile My GitHub profile

Get To Know More

About Me

Experience icon

Experience

4+ years
Generative AI & Full-Stack Engineering

Education icon

Education

M.S. Computer Science
University of North Texas, 2025

B.E. Computer Science
KL University, 2023

I'm a Generative AI Engineer at BN Associates, where I've spent the last two and a half years as lead engineer for an enterprise healthcare client. I first built their full-stack product (React/Next.js web, React Native mobile, Python services), and today I own the LLM, RAG, and agent work that runs on top of it.

I enjoy taking a business problem all the way to a service that's measured and monitored in production, using LangGraph agents, custom MCP servers, and grounded RAG. In healthcare every agent action has to be traceable, so I care about evaluation and governance as much as the model itself.

Arrow icon

Explore My

Experience

Generative AI Engineer

Jan 2026 – Present · Remote (Virginia, US)

BN Associates Inc.

  • Lead GenAI development for an enterprise healthcare client, owning chat, voice, document, and agent features end to end on one shared LLM, retrieval, and governance layer.
  • Designed stateful multi-agent workflows in LangGraph with checkpointers, retries, and subgraphs, so multi-step service requests finish with minimal hand-offs.
  • Built custom MCP servers connecting agents to ServiceNow, Salesforce, internal databases, and email. Agents read incoming messages and draft responses for human review.
  • Reworked retrieval, prompting, and grounding on Amazon Bedrock and SageMaker, which cut hallucination-driven chatbot errors by about 30%.
  • Set up LLM evaluation (groundedness, relevance, accuracy, latency) and sent low-confidence cases to a human reviewer. Also added PII masking and audit logging, so every agent action can be traced.
LangGraph CrewAI MCP Anthropic Claude GPT-4 LLaMA + LoRA Pinecone Neo4j Bedrock Azure AI Foundry

Full Stack Engineer

Mar 2024 – Jan 2026 · Remote (Virginia, US)

BN Associates Inc.

  • Lead full-stack and AI engineer for the same healthcare client, shipping a React/Next.js web app, a React Native mobile app, and scalable Python backends.
  • Built a voice assistant and IVR flow with AWS Lex, Transcribe, and Polly that reused the chat assistant's LLM/RAG layer instead of a second stack.
  • Built document processing with OpenCV, OCR, and a CNN classifier, cutting manual document review time by about 40%.
  • Fine-tuned BERT for intent and entity recognition, which improved NLU accuracy by about 25% over the previous baseline.
  • Automated model rollout with AWS CDK, Lambda, and ECS Fargate, taking new-model releases from days to hours.
React Next.js React Native FastAPI Django GraphQL PyTorch AWS Lex Terraform Kubernetes

Full Stack Engineer – Healthcare Domain

Apr 2022 – Jun 2023 · Hyderabad, India

Infosys

  • Built and maintained healthcare applications and REST services in Python, Django, JavaScript, and SQL.
  • Tuned data-heavy Django views and SQL queries, cutting page-load time by about 20%.
  • Automated reports, data cleanup, and API ingestion with Python and Apache Airflow, reducing manual effort by about 30%.
Python Django JavaScript SQL / PL/SQL Apache Airflow ELK Stack

Technical Skills

Generative AI & Agents

Checkmark

LLMs

GPT-4, Claude, LLaMA

Checkmark

LangGraph

LangChain, CrewAI

Checkmark

MCP

Custom servers

Checkmark

RAG

Pinecone, FAISS

Checkmark

Fine-Tuning

LoRA, BERT

Checkmark

Evaluation

Guardrails, HITL

Full-Stack Development

Checkmark

Python

FastAPI, Django

Checkmark

React

Next.js, Native

Checkmark

TypeScript

JavaScript

Checkmark

Node.js

REST APIs

Checkmark

APIs

GraphQL, gRPC

Checkmark

Databases

PostgreSQL, Redis

Cloud, ML & DevOps

Checkmark

AWS

Bedrock, SageMaker

Checkmark

Azure & GCP

OpenAI, Vertex AI

Checkmark

Deep Learning

PyTorch, TensorFlow

Checkmark

Containers

Docker, Kubernetes

Checkmark

CI/CD

Terraform, Jenkins

Checkmark

Observability

OpenTelemetry, ELK

Arrow icon

Browse My Recent

Projects

Featured Work in Production

Multi-Agent Healthcare Workflows

Stateful LangGraph agents that plan, check each other's work, and carry multi-step service requests to completion. Low-confidence cases go to a human before any final action.

LangGraphCrewAIClaudeA2A

Grounded RAG Assistant

Retrieval over approved enterprise knowledge, with a Neo4j knowledge graph for questions that span users, documents, roles, and organizations.

About 30% fewer hallucination-driven errors

PineconeWeaviateNeo4jBedrock

MCP Servers & Enterprise Integrations

Custom MCP servers give agents scoped access to ServiceNow, Salesforce, internal databases, and email. Agents read incoming messages, pull out what matters, and draft replies for review.

MCPFastAPIServiceNowSalesforce

Voice Assistant & IVR

A voice-enabled healthcare assistant that reuses the chat assistant's LLM and RAG layer, so there is only one stack to maintain.

AWS LexTranscribePolly

Intelligent Document Processing

OpenCV cleanup, OCR, and a CNN classifier behind a secure upload flow. The same flow feeds the embedding pipeline.

About 40% less manual review time

OpenCVOCRTensorFlow

Healthcare NLU Models

BERT models fine-tuned for intent classification and entity recognition on healthcare requests, then exported to ONNX and quantized for fast serving.

About 25% higher NLU accuracy

BERTPyTorchHugging FaceONNX

Client work is described in general terms to respect confidentiality.

Personal Projects

Parenting Navigator

Parenting Navigator

Full-stack web app built with React, Node.js, and MongoDB.

Portfolio website

Portfolio Website

This site: responsive HTML, CSS, and JavaScript, hosted on Netlify.

More projects on GitHub

More on GitHub

Experiments, coursework, and side projects.

Arrow icon

Credentials & Learning

Certifications

Certificate icon

Google AI Professional Certificate

Google · Coursera · Nov 2026

Certificate icon

AI Fundamentals

Google · Coursera · Nov 2026

Certificate icon

AI for App Deployment

Google · Coursera · Nov 2026

Certificate icon

Generative AI: Prompt Engineering Basics

IBM · Coursera · Nov 2025

Certificate icon

Getting Started with Git and GitHub

IBM · Coursera · Nov 2025

Certificate icon

Python for Data Science, AI & Development

IBM · Coursera · Oct 2025

Certificate icon

House of Code (Campus Edition) – MCQ Challenge

Lowe's Companies, Inc. · via Unstop

Arrow icon

Get in Touch

Contact Me

Based in Dallas, TX and open to relocation, hybrid, or remote roles. The quickest way to reach me is email or LinkedIn.