I design and deploy machine learning systems — not just models.
My work focuses on building reproducible, production-ready ML pipelines, combining strong modeling fundamentals with engineering discipline. I care about experimentation, robustness, and scalable deployment.
- End-to-end ML workflows: preprocessing → training → validation → inference
- Model optimization, hyperparameter tuning & evaluation
- Computer Vision & applied ML research
- Experiment-driven development
- Dockerized ML workflows
- CI/CD automation for ML pipelines
- Experiment tracking & model versioning
- Infrastructure as Code
- Cloud fundamentals (AWS ecosystem)
- Linux-based development environments
- Git workflows & automation
- Edge ML deployment on ESP32 (TinyML concepts)
- Real-time inference under resource constraints
My core identity lies in Machine Learning & Deep Learning,
strengthened by evolving MLOps and cloud engineering skills.


