- Bengaluru, Karnataka, India
- Staff
Take ownership of complex, open-ended data science problems and turn them into reliable, repeatable, production-ready workflows.
Responsibilities
- Own data science problems end to end: Translate complex, open-ended business and technical problems into well-defined data science solutions.
- Apply statistical methods to real-world problems: Use probability distributions, hypothesis testing, confidence intervals, experimental design, sampling, causal inference, time-series analysis, and simulation techniques to derive insights, test assumptions, and distinguish meaningful results from statistical noise.
- Build and evaluate machine learning models: Develop regression and classification models using appropriate techniques, ranging from linear and logistic regression to decision trees, random forests, gradient boosting, and neural networks.
- Build repeatable data science workflows: Design and implement end-to-end pipelines covering data preparation, modelling, validation, and reporting.
- Generate synthetic data and build simulations: Create realistic synthetic datasets with known ground truth when real-world data is limited or unavailable.
Requirements
- Nice to have: Semiconductor manufacturing experience
- Nice to have: Semiconductor manufacturing workflows
- Nice to have: Fab-to-test causal chain understanding
- Nice to have: Digital twins development
- Nice to have: Causal simulations of physical and operational processes
.png?1785784832)