At Universal Display Corporation (Nasdaq: OLED) (UDC), we’re changing the way people see the world.
If you’re reading this on a smartphone, there’s a good chance UDC’s materials are producing the light and color shining from your screen right now. UDC’s OLED ingredients are key parts of stunning, energy-efficient displays used in everything from smartwatches to phones, tablets, laptops, monitors, TVs and automobiles. Virtually every OLED consumer electronics product around the world uses UDC’s phosphorescent OLED materials and technologies.
UDC is a publicly traded company and pioneer in the OLED industry. When you join our global team, you are embarking on a journey at the forefront of display technology and organic electronics that impacts the daily lives of people around the world. From engineers to chemists, Ph.D. scientists, technicians, lawyers and more, our UDC team is continuously advancing our field. With a focus on energy efficiency, UDC’s team is contributing to making a better, more sustainable planet. Please visit us at www.oled.com.

JOB SUMMARY:

Universal Display Corporation is seeking a Research Scientist to apply inferential and generative artificial intelligence (AI) methods across a broad range of chemistry domains. As a key player in our multidisciplinary team, the Scientist will be at the forefront of developing machine learning models that predict chemical properties and design new compounds and materials. The ideal candidate is knowledgeable about the latest advancements in AI/ML and can lead exploratory research projects independently, contributing to cutting-edge academic research.

Key Responsibilities:

• Design and implement state-of-the-art machine learning models (e.g., tree-based algorithms, fingerprint-based methods, multi-layer perceptrons, and graph neural networks) to predict chemical and material properties with unparalleled accuracy.
• Develop and apply generative AI techniques to propose new molecules or materials with desired target properties that push past the limitations of today’s OLEDs.
• Continuously refine and validate predictive models to improve accuracy and reliability ensuring they meet the highest standards for molecular property prediction and compound design.
• Work closely with team members in the computational group to seamlessly integrate AI approaches with traditional chemical research methods such as laboratory experiments, molecular simulations, and quantum chemistry calculations.
• Partner with other R&D scientists to interpret model predictions, guide experiment design, and identify promising leads for new compounds or materials.

Required Qualifications:

• PhD in Chemistry, Physics, or a related field (e.g., Chemical Engineering, Materials Science).
• Proven experience applying machine learning to chemical problems, including developing both property prediction (inferential) models and generative models (demonstrated through peer-reviewed publications or successful practical applications).
• Familiarity with a broad range of machine learning approaches relevant to chemistry, such as tree-based models, fingerprint-based similarity methods, multi-layer perceptrons (MLPs), and graph neural network models.
• Proficiency in Python for scientific programming and data analysis, including experience with relevant libraries/frameworks (e.g., PyTorch, RDKit, PyG, etc.).
• Excellent communication and collaboration skills, with the ability to work effectively in a multidisciplinary team environment.

Preferred Qualifications:

• Postdoctoral research experience (2+ years) or equivalent advanced research experience applying AI/ML in chemistry.
• Background in organic electronics or related fields (e.g., OLED materials, organic semiconductors) is highly valued.
• Experience with machine learned interatomic potentials (MLIP) including training and implementation is a plus.
• Experience developing user interfaces or graphical tools for scientific software applications (GUI design skills).

• Design and implement state-of-the-art machine learning models (e.g., tree-based algorithms, fingerprint-based methods, multi-layer perceptrons, and graph neural networks) to predict chemical and material properties with unparalleled accuracy.
• Develop and apply generative AI techniques to propose new molecules or materials with desired target properties that push past the limitations of today’s OLEDs.
• Continuously refine and validate predictive models to improve accuracy and reliability ensuring they meet the highest standards for molecular property prediction and compound design.
• Work closely with team members in the computational group to seamlessly integrate AI approaches with traditional chemical research methods such as laboratory experiments, molecular simulations, and quantum chemistry calculations.
• Partner with other R&D scientists to interpret model predictions, guide experiment design, and identify promising leads for new compounds or materials