🚀 Building production-grade AI systems with MLOps, LLMs, and scalable cloud infrastructure.
⭐ Open to Machine Learning / MLOps / AI Engineer roles
- Designed and deployed scalable ML pipelines using CI/CD, Docker, Kubernetes
- Built LLM systems (RAG + Multi-Agent) using LangChain & Groq
- Deployed real-world systems on AWS & GCP
- Implemented monitoring with Prometheus & Grafana
- Developed end-to-end ML lifecycle systems (data → training → deployment)
MLOps:
CI/CD • Docker • Kubernetes • MLflow • DVC
Machine Learning:
Scikit-learn • TensorFlow • PyTorch
LLM Systems:
LangChain • RAG • Vector DB • Groq
Cloud & Infra:
AWS • GCP • Jenkins
Backend:
Flask • FastAPI
-
MLOps Pipeline Platform
End-to-end reproducible ML pipeline with MLflow, DVC, CI/CD, Docker, Kubernetes -
NLP Sentiment Pipeline
Production NLP pipeline with CI/CD, monitoring, and scalable deployment
-
Consignment Prediction
ML system with ETL, Airflow, DVC, AWS, Hadoop, and web interface -
Kidney Disease Classification
End-to-end ML pipeline with CI/CD and deployed application
-
Flipkart LLM System
RAG-based production LLM system with Groq, LangChain, AstraDB -
AI Study Agent
Multi-agent LLM system with Kubernetes, Jenkins, and APIs -
AI Music Composer
AI music generation system using Music21 + LLM pipeline
- Machine Learning Projects
Core ML algorithms (Regression, Classification, Clustering, Ensemble)
- 🎯 Focus: MLOps + LLM Systems
- 📦 Strong in production deployment & pipelines
- 🚀 Goal: Build scalable AI systems used in real-world products