Certifications

Continuous upskilling (Complete list: See Documents) towards data-driven materials research. Below are the skills & motivations I am actively using.

Introduction to High-Throughput Materials Development · Georgia Tech · Nov 2024 · completed

  • Takeaway: HT library design, high-throughput characterization & property screening; PSP linkages and MGI-style workflows.
  • Applied in: Designed a materials knowledge graph and structured database linking raw data → features → results, and implemented structure–composition–property pipelines for high-throughput-style data organization and analysis (see Projects).

Materials Data Sciences & Informatics · Georgia Tech · Sep 2024 · completed

  • Takeaway: Materials informatics, 2-point statistics & PCA for structure, homogenization, and cyberinfrastructure for data integration.
  • Applied in: Informed project selection and built proficiency in end-to-end ML workflows—spanning PCA-driven structure/feature representation (e.g., SHAP) and feature engineering for modeling multiple target properties (e.g., formation energy, melting point, band gap) (see Projects).

Density Functional Theory · École Polytechnique · Oct 2025 · completed

  • Takeaway: Foundation (mathematical and historical) of DFT, XC approximation strategies, quality and accuracy of different approximations, Practical tips & Tricks in DFT studies.
  • Applied in: Executing end-to-end DFT workflows in Quantum ESPRESSO. see git.

Machine Learning Specialization · DeepLearning.AI/Stanford · April 2023 · completed

  • Takeaway: Supervised ML, trees/ensembles, unsupervised & recommenders, plus ML best practices.
  • Applied in: Modeling nonlinearity in Electromagnetic Sensors, building various targeted machine learning pipelines to predict different materials properties (see Projects, Masters Thesis).

Nanomaterials & Nanosensors Specialization · Technion · Dec 2025 · completed

  • Takeaway: Latest developments in nanosensors and nanotechnology.
  • Focus: Characterization, fabrication, application, and further research directions to improve nano-1D, 2D, or 3D sensors.

Generative AI for Data Scientists Specialization · IBM · Dec 2024 · completed

  • Takeaway: Prompt engineering and hands-on GenAI for data augmentation, feature ideas, and model refinement.
  • Applied in: Building a neuro-symbolic pipeline for bandgaps in Semiconductor using local Ollama client (see Projects), efficient prompting.