Open to New Opportunities

Hi, I'm Praneeth Devunuri

Senior AI Scientist @ Optym

I describe myself as the ε-guy. In reinforcement learning, the epsilon value represents exploration vs exploitation. I embrace this policy by constantly learning and applying complex algorithmic models to automate and optimize the physical and digital worlds. Transitioned from PhD research in Connected and Autonomous Vehicles (UIUC) to driving next-generation AI and optimization systems at Optym.

Praneeth Devunuri

Professional & Academic Affiliations

Optym
Optym
University of Illinois Urbana-Champaign
UIUC
Texas A&M University
Texas A&M
IIT Madras
IIT Madras

Technical Expertise & Core Focus

A unique synthesis of theoretical reinforcement learning, computer vision, and hands-on LLM engineering.

Generative AI & LLMs

  • Agentic Workflows (crewAI, LangGraph)
  • Hybrid RAG & Semantic Search
  • LLM Fine-tuning (LoRA, PEFT)
  • Inference Optimization (vLLM)

Reinforcement Learning

  • Q-Learning & Policy Gradients
  • Autonomous Control Algorithms
  • Simulation Modeling (SUMO, VISSIM)
  • Decision Processes (MDPs)

Computer Vision

  • Object Detection & Tracking (YOLO)
  • Image Processing (OpenCV)
  • Spatial-CNN (Lane Line Prediction)
  • Sensor Fusion (Drones & Vehicles)

Featured Generative AI Work

Showcasing current projects built in the LLM and multi-agent space.

View All Projects
Generative AI

Agentic RAG System for Technical Documentation

RAG LLMs Vector Databases Python LangChain

An enterprise-grade Retrieval-Augmented Generation (RAG) system engineered for high-accuracy question answering over complex developer documentation and multi-page PDFs.

Read full details
Generative AI

Fine-Tuning Code Llama with PEFT/LoRA

PEFT LoRA HuggingFace PyTorch LLMs

A specialized code-generation assistant developed by fine-tuning Code Llama (13B) on domain-specific repository patterns, improving codebase-specific code completions by 35%.

Read full details
Generative AI

Multi-Agent Software Engineering Workspace

Multi-Agent Systems crewAI Autogen LLMs

An autonomous agent workspace where a crew of specialized AI agents (Product Manager, Coder, QA Engineer, Tech Writer) collaborate to plan, write, test, and write documentation for small software features.

Read full details

Professional Journey

A timeline of my academic background and engineering transition.

2025 - Present

Senior AI Scientist

Optym

Optym

Developing and deploying state-of-the-art machine learning models, optimization algorithms, and Generative AI (LLM) workflows to solve complex logistics and transportation scheduling challenges.

2020 - 2025

Ph.D. Researcher & Doctoral Student

University of Illinois Urbana-Champaign

University of Illinois Urbana-Champaign

Researched intelligent transportation systems, reinforcement learning for signal controls, and Large Language Model (LLM) frameworks for transit data under Dr. Lewis Lehe. Graduated in 2025.

2018 - 2020

Graduate Assistant Researcher

Texas A&M University

Texas A&M University

Built autonomous ride-sharing simulations, modeled pricing schemes for Mobility-as-a-Service, and performed emergency vehicle response experiments.

2014 - 2018

Bachelor of Technology

Indian Institute of Technology, Madras

Indian Institute of Technology, Madras

Developed image processing frameworks for traffic extraction, created glass fragmentation test prototypes, and served as Webops Head.