Sagnik Roy

Distinguishing the signal from the noise

About Me

Sagnik Roy

Deep Learning & MLOps Developer & NLP Specialist

I am driven by the power of data and advanced computation to create intelligent systems. My passion lies in building, training, and deploying robust Deep Learning models that tackle complex, real-world challenges.

Specializing in Natural Language Processing (NLP), I am proficient in leveraging GRUs/LSTMs & transformer architectures for tasks like text generation, sentiment analysis, and semantic search.

Python PyTorch NLP Transformers BERT Models FastAPI Docker

Recent Articles & Blogs

Check my projects out

AutocompleteMe

GRU/LSTM based sentence AutoCompletion Model

Created two GRU & LSTM based machine learning models from scratch for autocompleting sentences by character level predictions using NLP. Compared performance & deployed via FastAPI & Docker.

PyTorch Python NLP Docker FastAPI
TRUST NSFW

TRUST NSFW Detection (w/ near SOTA benchmarks)

TRUST-NSFW-Classifier is a high-performance deep-learning solution engineered to solve the "Binary Bottleneck" of modern content moderation. Leverages Vision Transformer (ViT) architecture for granular, multi-dimensional safety scores.

PyTorch Python ViT Docker FastAPI
Mynd Notes

Notes Recognizer & Memory Based Chat System

A subpart of the personal project Mynd. This system recognizes handwriting from seemingly infinite spaces and builds an intelligent query-based chat system with persistent memory.

RAG Vector DB Gemini MLKit System Architecture

Contact

Message me on

or