Heart Disease Prediction — End-to-End MLOps System
End-to-end MLOps pipeline: data → training → FastAPI inference → Docker + Kubernetes deployment, with Prometheus/Grafana observability and automated GitHub Actions CI/CD.
I bridge the gap between AI research and real-world engineering. From ML pipelines and containerised inference APIs to campaign systems serving 20M+ users, I build things that actually ship, scale, and stay reliable.
Not notebooks. Real infrastructure, deployed and monitored.
End-to-end MLOps pipeline: data → training → FastAPI inference → Docker + Kubernetes deployment, with Prometheus/Grafana observability and automated GitHub Actions CI/CD.
Python + Prefect ELT pipeline ingesting multi-source data, achieving 90%+ model accuracy and 40% reduction in processing time enabling faster retraining cycles.
End-to-end ownership of large-scale in-app campaign delivery at HCLTech. Reached 20M+ users during Black Friday / Cyber Monday with zero critical post-launch issues across 40+ campaigns.
Pursuing M.Tech in AI/ML at BITS Pilani. Exploring LLM fine-tuning, RAG pipelines, and building AI agent systems. Open to MLOps, AI engineering, and backend roles.