🔬 ML Researcher in Medical Data Science | M.Sc. Artificial Intelligence & Robotics (GPA: 19.27/20, Graduated 2026)
I build leakage-aware, interpretable machine learning pipelines for clinical and multi-omics data, with a focus on oncology applications.
- Statistical Machine Learning — model evaluation, nested cross-validation, leakage control
- Multi-omics Data Integration — late fusion of clinical, transcriptomic, and genomic data
- Interpretable ML in Oncology — SHAP, feature stability, biomarker discovery
- External Validation & Generalizability — cross-cohort transfer, calibration
M.Sc. in Artificial Intelligence & Robotics (Graduated October 2026) Mazandaran University of Science and Technology, Babol, Iran
- GPA: 19.27 / 20 (equivalent to ~3.9 / 4.0)
- Thesis: "Leakage-Controlled Late Fusion of Clinical and Transcriptomic Data for Predicting Biochemical Recurrence After Radical Prostatectomy" — Code & Analysis
- Relevant coursework: Machine Learning, Statistical Learning, Deep Learning, Pattern Recognition, Optimization, Medical Image Analysis
Programming & Machine Learning Instructor (7+ years)
Instructor at Technical and Vocational Institutes, Jahad-e Daneshgahi, and private institutions across Mazandaran Province, Iran — teaching 200+ students in Python, Machine Learning, and Artificial Intelligence.
Institutional teaching:
- Technical & Vocational Training Centers — Python, Web Development
- Jahad-e Daneshgahi (ACECR) — Machine Learning, Artificial Intelligence
- Private institutes across Babol and Mazandaran — Python, ML, AI
Private tutoring:
- Domestic (Iran): One-on-one and small-group coaching in Python, ML, and AI
- International: Online private tutoring for students abroad
Teaching areas:
- Python Programming (Beginner to Advanced)
- Machine Learning (scikit-learn, XGBoost, model evaluation)
- Artificial Intelligence (search, optimization, neural networks)
- Web Development (Django, Vue.js) — early career focus
12 years of professional software engineering across web development and machine learning, transitioning into statistical ML research for medical applications. Recently graduated M.Sc. in Artificial Intelligence & Robotics (GPA: 19.27/20, 2026).
Machine Learning & AI (7+ years):
- ML/Statistics: scikit-learn, XGBoost, LightGBM, SHAP, imbalanced-learn
- Deep Learning: PyTorch, TensorFlow — familiar with CNN, RNN, LSTM, Transformer, GAN, VAE, SSGAN
- Applications: Image classification, generative models, medical imaging
- Data: NumPy, Pandas, Matplotlib, Jupyter
Engineering experience (12 years):
- Backend & Full-Stack: Python, Django, PHP, Laravel, REST APIs
- Frontend: JavaScript, TypeScript, Vue.js, jQuery, Sass
- Infrastructure: Docker, Nginx, Redis, PostgreSQL, MySQL, SQLite
- Practices: Design Patterns, TDD, AWS
Why this matters for PhD research: Reproducibility is a major challenge in ML research. My engineering background ensures that my research pipelines are not just scientifically sound, but also reusable, testable, and well-documented — a combination that is increasingly valued in top ML venues.
| Project | Focus | Highlights |
|---|---|---|
| Prostate Cancer BCR Prediction | Late Fusion of clinical + RNA-seq | M.Sc. Thesis; Nested-CV, 4 external cohorts, SHAP, TRIPOD-AI checklist |
| Breast Cancer Recurrence | METABRIC clinical + genomic | GWO feature selection, nested-CV, SHAP |
| Lung Cancer MultiOmics | mRNA + miRNA + Clinical | Late fusion, PSO, external validation |
ML / Statistics
Deep Learning
Data & Scientific Computing
