Data Scientist

Our company offers an industry-leading suite of Industrial Engineering software used by semiconductor manufacturers around the planet. To effectively monitor and control such environments, it is necessary to effectively model and analyze the data.

The complexity of modern semiconductor manufacturing offers a rich landscape of valuable opportunities and worthwhile problems to solve. We are looking for a candidate with a demonstrated track record of building, training, validating, and deploying inference models - including comprehending the time dependent aspects of the data.

This position offers a great opportunity to apply modern analysis and machine learning (ML) methods to range of challenging problems. Our company encourages publishing and presenting the results at scientific conferences and symposia.

Candidates with experience in semiconductor manufacturing, industrial engineering, operations research, and Oracle SQL/PLSQL are strongly preferred.

Requirements

Required qualifications:

· Bachelor’s in Industrial Engineering, Physics, Mathematics, or similar quantitative field

· 2+ years of data science experience (building, training, validating, and deploying ML models)

· Knowledge of Python, PyTorch, scikit-learn, numpy, pandas, scipy, or similar data science libraries in the Python ecosystem

· Experience performing exploratory data analysis (working knowledge of data analysis, visualization, and statistics applied in a real-life environment)

· Familiarity with time series modeling methods (ARIMA / SARIMAX, Recurrent Neural Networks)

· Familiarity with sequence modeling/analysis (Markov chains, Hidden Markov Models, Kalman filtering, transformers)

Preferred qualifications:

· Master’s degree with analytical focus (e.g. Machine Learning, Applied Mathematics, Statistics, etc.)

· 3+ years experience in Semiconductor Manufacturing, ideally in Industrial Engineering or Operations Research areas

· Experience applying time series analysis and sequence modeling in operational environment

· Experience using Machine Learning methods to outperform statistical baselines

· Experience writing production-level code, especially in Python

· Deep knowledge of Oracle SQL & PL/SQL