Skip to content
View jonathanjohn8884's full-sized avatar
  • Chennai, India

Block or report jonathanjohn8884

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 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

Hi, I'm Jonathan J 👋

AI/ML Engineer — building production GenAI systems, RAG pipelines, and agentic AI workflows.


🧠 What I build

  • 🔍 RAG pipelines with RAGAS evaluation (faithfulness 0.91)
  • 🤖 Multi-step agentic AI workflows with LangGraph + LangSmith
  • 🌏 Indic NLP — Hindi/Tamil text classification with MuRIL + PEFT/LoRA
  • 👁️ Computer vision — YOLOv8 object detection at 92% accuracy
  • ⚡ Production model serving — vLLM + TorchServe + FastAPI + Docker

🛠️ Stack

PythonPyTorchLangChainHuggingFaceFastAPIDockerAWSMLflow


📁 Featured Projects

ProjectDescriptionKey Result
arXiv RAG Research AssistantRAG pipeline for research paper Q&A — LangGraph, LangSmith, RAGASFaithfulness 0.91
Indic NLP Text ClassifierHindi/Tamil classification — MuRIL + PEFT/LoRA, MLflow, W&B87%+ F1
YOLOv8 Handwritten OCRHandwritten word detection — TorchServe REST endpoint92% accuracy

📫 Connect

LinkedInEmail

📍 Chennai, India — open to relocate anywhere in India

Pinned Loading

  1. indic-nlp-text-classifierindic-nlp-text-classifierPublic

    Hindi/Tamil text classification using MuRIL + PEFT/LoRA — MLflow experiment tracking, W&B, FastAPI serving

  2. yolov8-handwritten-ocryolov8-handwritten-ocrPublic

    YOLOv8 handwritten word detection on scanned forms — 92% accuracy, TorchServe REST endpoint, Docker