Software Developer | Machine Learning, Backend & AI Products
I specialize in bridging the gap between prototypes and production. Whether it's training AI models with high accuracy, engineering robust data pipelines, or automating hours of manual workflows into minutes, my focus is on building scalable, real-world systems.
- Applied AI & ML: Training models and deploying them as production-ready REST APIs with a focus on explainability and out-of-distribution (OOD) robustness.
- Backend & Data Engineering: Building fault-tolerant architectures and scalable ETL pipelines that handle heavy data efficiently.
- RPA & Automation: Developing resilient, multi-threaded automation scripts that drastically reduce operational costs.
- AI & Data:
TensorFlowScikit-LearnOpenCVPandasDask - Backend:
PythonFlaskSQLPostgreSQLREST APIs - Automation:
SeleniumAppiumMultithreadingUiAutomator2 - Tools:
DockerGitGCP APIs
| Project | Description |
|---|---|
| wbc-analyzer | End-to-end WBC classification system deployed as a Flask REST API. Features a custom lightweight architecture (DenseNet121 + WBCAttention + MedSwish) with 7.83M parameters. Incorporates inference-time domain adaptation achieving a +32.09 pp out-of-distribution (OOD) accuracy boost (89.05% on unseen hardware). Includes a two-layer shortcut learning guard and an autonomous multi-modal LLM agent (GPT-4o & Gemini 2.5 Flash) for clinical explainability. Achieved 98.53% in-distribution accuracy. |
| popcorn-wagon | Hybrid movie recommender engine built with Dask/Pandas for scalable ETL and sub-millisecond similarity search. |
| portal-cleaner-ultimate | Modular RPA suite featuring a custom local test harness for offline simulation. Engineered with fault-tolerant retry logic, reducing manual workloads by over 90%. |
| listing-pilot | Appium-powered Dolap & Gardrops mobile marketplace automation bot. |