Day to Day Responsibilities
61 Develop physics-based models of nonlinear, multivariable systems and subsequently embed the physics of those models into algorithms to control the system dynamics by utilizing advanced model-based control design techniques
61 Utilize machine learning methods to develop process monitoring and fault detection tools and/or classification/regression models for solving important manufacturing problems.
61 Build/develop supervisory control layer for calculating optimal setpoints for process control in a manufacturing system; this will require coordinating and synchronizing the existing physics-based/***-principles models to provide an overall plant process view.
61 Develop in-depth knowledge of Corning processes to build technical understanding for key process steps by using rigorous scientific knowledge.
61 Lead project teams and work closely with other teams to implement/deliver advanced control solutions and potentially other advanced process technologies
61 Work in a multi-disciplinary environment where there will be collaboration between experts from other teams.
61 Generate intellectual property through technical reports, invention disclosures, and patent applications
Education & Experiences
61 Ph.D. or Masters (+3 years of manufacturing experience) in Chemical, Mechanical or Electrical Engineering discipline
61 Direct experience with data analysis, machine learning (ML), advanced controls technologies and/or ***-principles/physics-based modeling
Required Skills
61 Evaluate existing process control strategies and propose and develop enhancements. Utilize multivariate statistical methods and machine learning for LCD glass making process improvement.
61 Design and develop process controls solutions (especially model-based control techniques) for manufacturing processes. Work closely with manufacturing to develop appropriate hardware and software platforms for implementing control solutions.
61 Familiarity with optimization theory and controls technologies such as optimal control, robust control, adaptive control, model predictive control (MPC), non-linear approaches, and traditional PID control
61 Experience with developing data-driven (system identification) / physics-based models (finite element models, mass and energy balances, etc.) for manufacturing process optimization
61 Extensive knowledge of ML techniques/algorithms (e.g., neural networks, random forests, etc.) and their mathematical foundation
61 Proficient in Matlab/Simulink and working knowledge of Python, C/C++, .NET.
61 Must have: (1) a thorough understanding of relevant scientific concepts, principles, and theory, particularly relating to general machine learning and algorithms and fundamental physics principles; (2) experience demonstrating broad application of those concepts in real-world settings.
Desired Skills
61 Skills that can be demonstrated in PLC and IEC based programming (ladder, structured text)
61 Background in multivariate statistics tools, such as principal component analysis (PCA) and partial least squares (PLS) regression
61 Experience with real-time control systems, data acquisition, and data interpretation
61 Experience using machine learning packages such as Tensorflow/Keras, PyTorch, Scikit-Learn.
61 Experience with formal language models (finite state automaton (FSA), Petri net, Symbolic model, etc.), graph theory and finite abstraction
61 Ability to work in a manufacturing environment
Soft skills
61 Project leadership
61 Communication skills in a variety of situations – from gathering operator insight to stakeholder presentations
61 Collaboration across a multi-disciplinary group
61 Strong verbal and written skills
61 Excellent interpersonal skills
61 Ability to prepare and present presentations effectively
61 Functions well on projects and team initiatives as well as independent assignments
61 Strong technical curiosity with desire to take on challenging technical problems