Key Responsibilities
Design, implement, and evaluate machine-learned interatomic potentials for organometallic and organic materials, including multistate potentials for excited-state applications.
Develop and benchmark neural network architectures, including equivariant graph neural networks and graph transformers, for interatomic potentials and molecular property prediction.
Fine-tune foundation interatomic potentials using proprietary data, and build training sets efficiently through active learning and targeted DFT calculations.
Apply MLIPs to reactivity, degradation, and molecular-dynamics studies, including automated reaction-discovery workflows.
Integrate MLIPs and predictive models into agentic AI workflows and scientific applications that support chemistry-focused decision-making.
Curate DFT datasets and contribute to applied AI/ML infrastructure that enables reproducible model development, benchmarking, deployment, and monitoring.
Collaborate with ML scientists, computational chemists, synthetic chemists, and device engineers to interpret model outputs and guide modeling and architecture decisions.
Required Qualifications
Ph.D. in Chemistry, Chemical Engineering, Materials Science, Physics, or a related field, with demonstrated experience developing machine-learned interatomic potentials or ML force fields.
Proven experience designing or substantially modifying neural network architectures for molecular or atomistic systems, such as equivariant graph neural networks and related MLIP architectures (for example, NequIP, MACE, Allegro, UMA, AIMNet, or DPA).
Strong working knowledge of density functional theory, including the generation and quality assessment of training data.
Proficiency in Python for scientific programming, including hands-on experience with PyTorch, ASE, RDKit, and related scientific Python libraries.
Experience validating ML potentials beyond energy and force errors, including molecular-dynamics stability and out-of-distribution behavior.
Excellent communication and collaboration skills, with the ability to work effectively across scientific and engineering disciplines.
Preferred Qualifications
Advanced research experience applying MLIPs to transition-metal complexes, organometallic chemistry, reactive systems, or transition states.
Experience with excited-state, multistate, or multi-fidelity machine-learned potentials.
Experience fine-tuning foundation interatomic potentials or other pretrained atomistic models.
Experience with active learning, uncertainty quantification, or automated training-data generation for atomistic models.
Experience with molecular-dynamics and molecular-simulation workflows (for example, LAMMPS, OpenMM, or ASE), or enhanced-sampling techniques such as Nanoreactor.
Background in molecular chemistry, organic electronics, OLED materials, or organic semiconductors.
Experience with agentic AI workflows or LLM tool harnesses that connect models, tools, and data.
Current Benefits at UDC
Competitive base salary and annual bonus program
Medical/Prescription Drug coverage, Dental, and Vision for employees and family
Option of Health and Dependent Flexible Spending Accounts (FSAs)
Option of Health Savings Account (HSA)
Group Term Life insurance, short term disability, and long-term disability benefits for employees
Employee Stock Purchase Plan (ESPP)
401(k) company contribution
Ewing Worldwide Headquarters (HQ) cafeteria provides breakfast and lunch to employees at no cost to them
Annual charitable matching gift
Generous Paid Time Off
Annual compensation range: $115k-140k
At Universal Display Corporation, base pay is one part of our total compensation package. Individual compensation is determined by skills, qualifications, experience, and location. Compensation details listed in this posting reflect the annual salary range only, and does not include bonus, equity or sales incentives, if applicable.