🚀 Passionate Data Scientist & ML Engineer with hands-on experience in Time Series Forecasting, Deep Learning, and Real-time Data Systems.
I love building end-to-end intelligent data pipelines — from ingestion to model deployment — using GCP, Python, and open-source frameworks.
🎯 Current Focus Areas:
- Building real-time streaming pipelines with Apache Airflow, Kafka, Spark, and Cassandra (Dockerized on GCP).
- Developing a Flask-based ERP System integrated with Google Sheets & Drive APIs for smart hub management and analytics.
☁️ Cloud Skills:
- GCP Data Services: BigQuery, Dataflow, Dataproc, Pub/Sub, Cloud Composer (Airflow), Cloud Storage
- MLOps & AI Tools: Vertex AI, AI Platform Pipelines, and Cloud Run for model deployment
- Infrastructure: Docker, Cloud Build, IAM, VPC networking
📚 Learning Journey:
Exploring MLOps, Vector Databases, and Lightweight LLMs for Synthetic Data Generation.
📫 Reach me: anuragmukati09@gmail.com
⚡ Fun Fact: I code with empathy — because great tech should make life easier for others 💙
- ☁️ GCP Data Pipeline Automation — Airflow + Dataflow + BigQuery workflow for automated data ETL and ML preprocessing.
- 📊 Flask ERP System — Lightweight ERP connected with Google Sheets/Drive for delivery hub management.
- ⚙️ Real-time Streaming Analytics — Kafka + Spark + Cassandra with Docker on GCP for high-throughput processing.
- 🧠 Synthetic Data Generator — Lightweight LLM-powered SQL → CSV data generation engine using Faker library.