Skip to content
View Sainava's full-sized avatar

Highlights

  • Pro

Block or report Sainava

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
Sainava/README.md

coding gif

Hello There, I am Sainava Modak

About Me

Computer Science student | AI | Research | Systems Engineering

My work spans computer vision, generative AI, and machine learning, with a growing focus on building reliable and practical systems around research ideas. I enjoy working across different layers of technology, from model development and experimentation to backend systems, distributed applications, and open source software.

Open Source

Contributed to CERN ROOT, Hugging Face Transformers, and NVIDIA NeMo,and always looking for interesting projects to contribute to and learn from.

Beyond Code

Selected as one of the winners of Talent for Japan 2025. It was an opportunity to work beyond my usual technical environment, collaborate across different backgrounds, and explore how technology can address real world problems.

Outside of technology, I love football ⚽️❤️.

🌐 Socials

CodeStudio

Tech Stack

Programming

PythonC++Java

AI & Machine Learning

PyTorchHugging FaceOpenCVYOLOGraph Neural NetworksRAG

Backend & Distributed Systems

Spring BootRedisApache KafkaWebSockets

Databases

MySQLPostgreSQLNeo4j

Cloud & Tools

AWSDockerGitGitHubCI/CD

GitHub Stats

Main Stats

Streak Stats

Top Langs

GitHub Trophies

GitHub Trophies


Hacktoberfest & Open Source Badges

Holopin Badges

Pinned Loading

  1. CV-Graph-RAGCV-Graph-RAGPublic

    A hybrid GraphRAG system for computer vision literature synthesis, combining semantic vector search with a Neo4j knowledge graph of papers, methods, tasks, datasets, and metrics to provide grounded…

    Jupyter Notebook

  2. TacticalGNN-Spatial-Football-EngineTacticalGNN-Spatial-Football-EnginePublic

    A geometric deep learning and kinematics engine for spatial football analytics and prediction, powered by PyTorch (GNN)

    Python 1

  3. LingoStream-Springboot-BackendLingoStream-Springboot-BackendPublic

    A highly concurrent, distributed backend for real-time collaborative subtitle editing. Engineered with Redisson distributed locking, Redis cache-aside optimization, and STOMP WebSockets to solve da…

    Java

  4. DeepFake-DetectionDeepFake-DetectionPublic

    Detects deepfake videos by analyzing sequences of extracted features using a combined CNN (ResNet18) and RNN (Bi-LSTM) pipeline with optical flow for temporal consistency.

    Jupyter Notebook 2 1

  5. Sign-Language-to-SpeechSign-Language-to-SpeechPublic

    A real-time Sign Language to Speech system using YOLOv11, MediaPipe, and a CNN+LSTM pipeline to convert Indian Sign Language gestures into spoken words through an interactive web app.

    Jupyter Notebook 7 2

  6. DSA-in-CPPDSA-in-CPPPublic

    This repository documents my journey of learning DSA in cpp . It contains fundamental cpp concepts , data structures and their implementations, algorithms with their complexities documented and DSA…

    C++ 1