Skip to content
View shre-db's full-sized avatar

Block or report shre-db

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
shre-db/README.md

Shreyas

I'm a Deep Learning Engineer focused on building systems where models reason, act, and collaborate. With a foundation in physics and mechanical engineering, I specialize in applying AI especially vision + LLM systems to real-world tasks.

I’ve built agentic AI workflows using LangChain, LangGraph, and ReAct, such as Linked Squad (a multi-agent LinkedIn optimizer) and DoqToq (a modular RAG system that gives documents a voice). On the vision side, I work with GANs, LaMa, UNet, Pix2Pix, Diffusers, and Fourier pipelines for inpainting, segmentation, and image generation.

I focus on scalable, optimized deployment building pipelines with PyTorch DDP, Docker, and Flask and I enjoy turning research ideas into robust, usable systems.

My toolkit includes PyTorch, Hugging Face, LangChain, LangGraph, MLflow, GCP, and more. If you're building something in LLMs, agentic AI, or generative vision I’d love to connect.😃

  • 🌍  I'm based in Mangalore
  • ✉️  You can contact me at shreyasdb99@gmail.com
  • 🚀  I'm currently working on DoqToq

Skills

Python Python Python PyTorch PyTorch-Lightning Julia NumPy Pandas Matplotlib Seaborn Scikit-Learn Hugging Face OpenCV  Linux Docker Git  MLflow GCP Streamlit Hydra PostgreSQL Flask Excel Jira Notion

Socials

           

Badges

My GitHub Stats

shre-db's GitHub stats

Pinned Loading

  1. doqtoq doqtoq Public

    Documents that talk ‒ DoqToq

    Python

  2. linked-squad linked-squad Public

    An AI-powered career assistant that transforms your LinkedIn profile, evaluates job fit, and guides your job search with smart, personalized insights.

    Python

  3. A-Curious-FFN A-Curious-FFN Public

    This project utilizes Artificial Curiosity in a Feed-Forward Network to recognize manipulated images.

    Jupyter Notebook

  4. Stateful_Transformers Stateful_Transformers Public

    Custom Scikit-Learn based Transformers and Pipelines for Feature Engineering.

    Python

  5. OCT-Retinal-Disease-Detection-CNN OCT-Retinal-Disease-Detection-CNN Public

    Retinal disease detection using optical coherence tomography (OCT) and deep neural networks.

    Jupyter Notebook 6 4

  6. United-States-Coal-Usage-Classification United-States-Coal-Usage-Classification Public

    This end-to-end machine learning project is focused on analyzing coal usage in the United States from 2001 to 2021 and classifying coal using data gathered from the U.S. Energy Information Administ…

    Jupyter Notebook 1