I am a Ph.D. candidate in Mechanical Engineering at Michigan State University, developing physics-based, data-driven, and uncertainty-aware computational frameworks for complex materials and engineering systems.
My work lies at the intersection of:
- 🧩 Computational mechanics and constitutive modeling
- 📊 Uncertainty quantification and Bayesian inference
- 📈 Sensitivity analysis
- 🌊 Computational fluid dynamics
- 🤖 Machine learning and scientific AI
- 🔊 Generative modeling for speech and audio
My doctoral research focuses on fractional-order constitutive modeling of polyurea and its nanocomposites. I develop reproducible computational frameworks that integrate experimental viscoelastic data with deterministic optimization, sensitivity analysis, Bayesian inference, and uncertainty propagation.
The goal is to build material models that are accurate, parsimonious, interpretable, and ready for engineering simulations.
I also have experience in multiphase and multiphysics CFD, including:
- Double-emulsion generation in shear-thinning fluids under electric fields
- Non-Newtonian blood flow through stenotic arterial geometries
- Custom ANSYS Fluent UDF development
- Numerical verification, validation, and flow-field analysis
My recent work extends into machine learning and generative AI for speech and audio applications.
I have developed end-to-end ML pipelines for speech-based anxiety screening and contributed to vehicle-cabin audio synthesis workflows involving acoustic-scene composition, pretrained model adaptation, parameter-efficient fine-tuning, and model evaluation.
Python · MATLAB · PyTorch · PyMC · scikit-learn · SALib · Snakemake · SLURM · Git
- Scientific machine learning
- Generative audio modeling
- Parameter-efficient fine-tuning
- Reproducible research software
- Uncertainty-aware engineering models
I am interested in research and R&D opportunities involving scientific computing, machine learning, uncertainty quantification, computational mechanics, and generative audio.