Available for new AI builds

Devaraj Kudumula

AI/ML Engineer & Researcher

I ship production LLM systems — advanced RAG, agentic (ReACT) frameworks, and LangGraph orchestration serving 10K+ daily users — and research what keeps them fast, cheap, and reliable.

See my workEnter AI-SpaceResume
Chennai, India · devaa.kudumula@gmail.com
Devaraj Kudumula
● LIVE
3+
Years Experience
10K+
Daily Users
40%
LLM Cost Cut
01ABOUT

An engineer who ships AI. A researcher who keeps exploring.

I build enterprise-grade AI by day and dig into the research that powers it by night — LLM orchestration (LangChain, LangGraph), advanced RAG, and agentic frameworks, with active reading and tinkering across NLP, agentic AI, LLMs, and computer vision.

3+
Years Experience
10K+
Daily Users
40%
LLM Cost Cut
50%
Latency Cut
2×
Spotlight Awards
6+
Systems Shipped

/ What I build

/ What I research

02EXPERIENCE

From research prototype to production scale.

Three years building AI that ships, hardens, and earns trust at enterprise scale.

AI/ML Engineer

Intellect Design ArenaChennai, Tamil Nadu

Jun 2023 — Present
  • Architected and deployed enterprise LLM applications on Gemini and OpenAI with LangChain, used by 10,000+ people daily across several business units.
  • Led a company-wide AI assistant: secure answers from internal documents, live web search, and agents that teams can build and plug in themselves.
  • Designed a LangGraph orchestration layer that runs conditional multi-agent workflows with no model calls at decision points, cutting cost ~40% and latency ~50%.
  • Built an adaptive retrieval pipeline: query planning, intent-driven metadata filtering, agentic routing, and follow-up loops that cover every entity in a question.
  • Shipped a ReACT agent runtime with adaptive reasoning and automatic recovery from failed tool calls, keeping multi-step agents dependable.
  • Built a document ingestion service that rebuilds layouts, tables and figures with fine-grained position data, giving downstream AI clean, structured input.
LangChainLangGraphGeminiOpenAIFastAPIMongoDBDockerKubernetesGCP

Data Science Intern

Caterpillar Inc.Chennai, Tamil Nadu

Jan 2023 — Jun 2023
  • Built a Transformer-based NLP pipeline processing 100k+ comments/month with 92% sentiment classification accuracy and predictive trend insights.
  • Fine-tuned a domain-specific Transformer summarizer — cut manual review time by ~90%, turning days into minutes.
  • Designed a real-time analytics dashboard for service diagnostics and anomaly detection across distributed systems.
  • Migrated legacy SAS pipelines to Python — better scalability, faster execution, lower infra cost.
TransformersPyTorchPythonPlotlySAS→Python
03PROJECTS

Things I've built. Things people use.

A selection of LLM systems, agentic architectures, and ML platforms — most in production today.

~/projects/enterprise-ai-assistant running
What changed in the travel policy this quarter?

→ impact: Faster knowledge retrieval

Production · 10K+ DAU

Project 01: Enterprise AI Assistant

A conversational assistant for teams: secure answers from internal documents, live web search, and agents that people can build and plug in themselves.

  • Self-healing ReACT agents with adaptive reasoning
  • Picks the right tool or agent for each request
  • Runtime that scales to 10K+ daily users
LangChainLangGraphGeminiOpenAIFastAPIMongoDB

Impact

Faster knowledge retrievalLower inference costHigher decision velocity
01 / 06
04SKILLS

A pragmatic AI stack — tuned for reliability.

The tools and patterns I reach for to ship LLM systems that don't break in production.

Python

95%

LangChain

95%

OpenAI

92%

Git

92%

FastAPI

90%

PyTorch

88%

Docker

88%

Hugging Face

88%

MongoDB

85%

Gemini

85%

AWS

85%

Azure

85%

GCP

85%

GitHub Actions

85%

Bash

82%

TensorFlow

82%

Kubernetes

80%

Jenkins

80%

Plotly

75%

JavaScript

72%

/ Also fluent in — tap to expand

05RECOGNITION

Recognized work, certified craft.

A few highlights from the journey so far.

Spotlight Award×2

Intellect Design Arena

Two quarterly Spotlight Awards for high-impact enterprise AI delivery.

Google Data Analytics

Coursera

Professional Certificate in Data Analytics.

ML & Deep Learning Specialization

Udemy

End-to-end ML and deep learning specialization.

/ Education

Amrita Vishwa Vidyapeetham, Coimbatore

B.Tech. — Computer Science & Engineering (AI Specialization)

Jul 2019 — Jun 2023

06Contact

Have an AI idea?
Let's build it together.

Open to roles, collaborations, and AI builds — RAG systems, agent platforms, LLM optimization, or anything where models meet real users.

devaa.kudumula@gmail.comLinkedIn+91-6281003863