class JitendraKumar:
def __init__(self):
self.name = "Jitendra Kumar"
self.role = "AI/ML Engineer & MLOps Enthusiast"
self.location = "India 🇮🇳"
self.focus = ["LLMs", "RAG Systems", "MLOps Pipelines", "Cloud AI"]
self.tools = ["MLflow", "DVC", "Docker", "AWS", "FastAPI"]
self.currently = "Building production-ready ML systems & exploring LLM architectures"
self.looking_for = "Open-source collabs on AI/ML and full-stack AI applications"
self.fun_fact = "I love breaking AI models just to make them better 😆🔥"
def say_hi(self):
print("Thanks for stopping by! Let's build something remarkable together 🚀")
me = JitendraKumar()
me.say_hi()| Project | What it does | Tech Stack | Link |
|---|---|---|---|
| AtlasAI — Full-Stack LLM & MLOps App | End-to-end AI web app with Flask backend, LLM intelligence, CI/CD via GitHub Actions, deployed on AWS EKS with Prometheus + Grafana monitoring. | 🔗 repo | |
| MLOps-Complete-ML-Pipeline | Production-grade ML pipeline using DVC for experiment tracking & data versioning, DVCLive for metric logging, and AWS S3 as remote storage backend. | 🔗 repo | |
| PitLane-RAG-AI | AI-powered Formula 1 assistant using Retrieval-Augmented Generation for real-time F1 knowledge querying and intelligent contextual responses. | 🔗 repo | |
| Intelligent QA Automation — Fintech | Automated quality assurance framework for fintech systems enabling intelligent test coverage, validation pipelines, and regression detection. | 🔗 repo | |
| Meta-Data Extraction from Documents | Python pipeline for extracting structured metadata from unstructured documents, enabling downstream indexing, analysis, and retrieval workflows. | 🔗 repo | |
| Load Prediction | ML model for predicting load patterns using EDA, feature engineering, and regression modeling with Jupyter Notebook-based experimentation. | 🔗 repo |

