ML Engineer / Data Scientist based in Sydney, building models that go beyond the notebook — from data pipelines to production.
- 🎓 Currently pursuing a Master of Computer Science (Advanced Entry) at the University of Sydney, specialising in Data Science & AI and Cybersecurity
- 💼 Previously a Data Scientist at Deloitte India, building Scala-Spark pipelines and analytics frameworks for enterprise audit data
- 🔭 Currently working on an ML Engineering capstone project (CMU Capstone, Sydney)
- 🌱 Focused on the full ML lifecycle: feature engineering, model development, and deployment (Docker, AWS, GCP)
- 💬 Ask me about computer vision, data pipelines, or turning messy data into something usable
- 📫 Reach me at dhruvsparee@gmail.com
- 🔗 Portfolio · LinkedIn
Languages: Python · Scala · SQL · Java
ML & Data Engineering: PyTorch · TensorFlow · Scikit-learn · Apache Spark · Spark-SQL · NLP · Computer Vision
MLOps, Cloud & Tools: Docker · AWS · Google Cloud · Databricks · Tableau · Power BI · Git · MySQL
| Project | Description |
|---|---|
| Victorian Crash Severity Classifier | Hierarchical two-stage XGBoost classifier predicting crash severity from Victoria's road crash data |
| CIFAR-10 Image Classification Comparison | Benchmarking PCA+SVM, MLP, and CNN approaches on CIFAR-10 — CNN reached 74.6% test accuracy |
| GridPulse | Real-time visualisation of Australia's electricity grid, streaming live NEM data over MQTT |
| Jade / Plant Leaf Disease Detection | VGG-19 based plant disease detection app — 3rd place, Smart India Hackathon |
| ExamGenerator | Turns lecture content into exam-style question papers via a simple JSON pipeline |