Skip to content
View BaluHarshavardan99's full-sized avatar

Block or report BaluHarshavardan99

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
BaluHarshavardan99/README.md

πŸ‘‹ Hi, I'm Balu Harshavardan Koduru

I am a passionate Machine Learning Engineer with experience developing AI solutions across various domains, specializing in Generative AI, Large Language Models (LLMs), Natural Language Processing (NLP), computer vision, and multi-agent systems. I have worked on creating impactful models using deep learning and reinforcement learning. Currently, I’m focused on advanced recommendation systems using Llama LLM. I’m seeking opportunities in AI/ML roles where I can leverage my skills to contribute to cutting-edge projects.

πŸ”§ Technologies & Tools

Python NumPy PyTorch TensorFlow Scikit-Learn Spacy Git AWS

πŸ’Ό Professional Experience

Machine Learning Researcher, SUNY RF

September 2022 - May 2024

  • Pioneered the first-ever image-caption dataset in endoscopy and developed a contrastive learning-based Visual Question Answering (VQA) model, EndoAssistant.
  • Fine-tuned LLaVA (LLM) for creating an AI assistant for endoscopic surgery.
  • Led the development of a Speech Therapy AI Agent, integrating deep learning models with clinical expertise.

Machine Learning Researcher, ACPS Group, Norway

January 2021 - June 2022

  • Implemented a Multi-Agent Reinforcement Learning algorithm for drone fleets.
  • Developed CNN models to classify UAVs based on radio signals and analyze human speech signals, achieving high accuracy.

Data Analyst, JSW Energy

June 2019 - December 2019

  • Developed deep learning models to predict Un-Burnt Carbon levels in thermal power plants, improving efficiency by 15%.
  • Conducted extensive EDA and built interactive dashboards in Tableau for data visualization.

🌟 Projects

  • EndoAssistant: Developed a Visual Question Answering (VQA) model for endoscopic surgery using CLIP and Whisper API.
  • Drone Fleet Control: Implemented a reinforcement learning algorithm for drone fleet management in Unreal Engine’s AirSim simulator.
  • Movie Database System: Created a comprehensive movie information system using Python and SQL, optimized for performance.

πŸŽ“ Education

  • Master of Science (MS) in Artificial Intelligence, University at Buffalo, The State University of New York (May 2024)
  • Master of Science (M.Sc.) in Physics, Birla Institute of Technology and Sciences Pilani (June 2022)
  • Bachelor of Engineering (B.E.) in Electronics and Instrumentation, BITS Pilani (June 2022)

πŸ“š Publications

πŸ“« How to reach me

Coding GIF


⭐️ From BaluHarshavardan99

Popular repositories Loading

  1. Mutli-Agent-Reinforcement-Learning-for-UAV-Fleet-Management Mutli-Agent-Reinforcement-Learning-for-UAV-Fleet-Management Public

    Work in Progress

    1

  2. Light-Weight-Deep-CNN-for-Background-Sound-Classification-in-Speech-Signals Light-Weight-Deep-CNN-for-Background-Sound-Classification-in-Speech-Signals Public

    Environment/Background Sound Classification in Speech Signals (Publication)

    MATLAB

  3. EndoSLAM EndoSLAM Public

    Forked from CapsuleEndoscope/EndoSLAM

    EndoSLAM Dataset and an Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearner

    Python

  4. Hallucination-in-Chat-bots Hallucination-in-Chat-bots Public

    Hallucination in Chat-bots: Faithful Benchmark for Information-Seeking Dialogue

    Python

  5. Object-Detection-Face-Mask-Detection Object-Detection-Face-Mask-Detection Public

    CSE 555: Pattern Recognition - Final Project

    Jupyter Notebook

  6. Classification-of-UAVs-using-TF-Analysis-of-Remote-Control-Signals-and-CNN Classification-of-UAVs-using-TF-Analysis-of-Remote-Control-Signals-and-CNN Public

    UAV Classification

    Jupyter Notebook