Technical Expertise
My skill set spans experimental materials science and modern machine learning infrastructure - from hands-on lab work to production ML systems.
Programming & Machine Learning
Programming & ML
Python

PyTorch, TensorFlow, scikit-learn

Machine Learning

Supervised, Unsupervised, Deep Learning

MLOps

MLflow, Airflow, Docker, GCP

Experimental Skills
Materials Characterization

SEM, Raman, Mechanical Testing

Data Analysis

Feature Engineering, Visualization

Experimental Design

DOE, Bayesian Optimization

Core Technologies

Programming Languages

  • Python (primary), Bash, SQL, LaTeX

ML/DL Frameworks

  • PyTorch, TensorFlow, Keras, scikit-learn, XGBoost
  • Specialized: Hugging Face Transformers, GPyTorch (Gaussian Processes)

MLOps & Infrastructure

  • Experiment Tracking: MLflow, Weights & Biases
  • Orchestration: Apache Airflow, DVC
  • Containerization: Docker, Docker Compose
  • Cloud: Google Cloud Platform (Cloud Run, Cloud Storage, Composer)
  • CI/CD: GitHub Actions, automated testing with pytest

Data Science Stack

  • NumPy, Pandas, Matplotlib, Seaborn
  • Statistical analysis and visualization

Experimental Capabilities

Materials Characterization

  • Scanning Electron Microscopy (SEM) - imaging and quantitative analysis
  • Raman Spectroscopy - structural characterization and feature extraction
  • Mechanical Testing - Instron universal testing, Dynamic Mechanical Analysis (DMA)
  • Sample preparation and processing

Laboratory Skills

  • Laser shockwave compaction systems
  • Electrical fusion equipment
  • Cleanroom fabrication protocols
  • Quantitative dimensional analysis from microscopy

Machine Learning Specializations

Core ML Techniques

  • Supervised Learning: regression, classification, ensemble methods
  • Unsupervised Learning: clustering, dimensionality reduction (PCA)
  • Deep Learning: CNNs, RNNs, Transformers, attention mechanisms
  • Feature engineering and selection for materials data

Advanced Methods

  • Bayesian Optimization with Gaussian Processes
  • Physics-Informed Neural Networks (PINNs)
  • Transfer learning and fine-tuning large models
  • Data-efficient learning strategies (LOOCV, small dataset techniques)

Generative Models

  • Variational Autoencoders (VAEs)
  • Generative Adversarial Networks (GANs)
  • Diffusion models
  • Protein language models (ProGen2)