MSc Computational Materials Science
TU Bergakademie Freiberg · Freiberg, Saxony, Germany
// summary
MSc student in Computational Materials Science at TU Bergakademie Freiberg, building deep learning and data systems for materials and semiconductor manufacturing: inverse molecular design, phase identification from MD simulations, wafer-map defect recognition, fab yield excursion analysis, and real-time inference at the equipment edge in C++/CUDA. Background in mechanical engineering.
TU Bergakademie Freiberg (TUBAF) · Freiberg, Germany
Focus: deep learning for molecular property prediction. Coursework in quantum mechanics, thermodynamics, and materials modelling.
Anna University · Chennai, India
Foundation in engineering principles, CAD, and manufacturing processes.
// ml
// languages
// data
// tools
// domains
In-line wafer-map watchdog at the equipment edge: zero-copy SECS-II decode, CPU/GPU spatial-signature detectors, FabEye's CNN on a custom CUDA inference engine, and a lot hold sent back to the tool in under a millisecond.
Fab yield excursion detection and root cause on a simulated fab with ground truth: SPC benchmarked against injected excursions, commonality analysis, wafer-map patterns from FabEye, real-time SPC on Kafka, and process ML on real fab data.
Wafer-map failure pattern recognition on the real WM-811K dataset, with a leakage audit, a controlled negative result, conformal prediction that holds on unseen lots, and an ONNX + FastAPI service.
Deep learning platform for inverse molecular design — start with a desired property, generate the chemical structure that satisfies it.
High-performance deep learning framework for thermodynamic phase identification from molecular dynamics simulations.