Senior Computational Materials Engineer - MLIPs

The group you’ll be a part of

In the Semiverse Solutions Team, we are dedicated to excellence in the virtual experimentation of Lam’s etch and deposition processes. We drive innovation to ensure our cutting-edge solutions are helping to solve the biggest challenges in the semiconductor industry.

As a Senior Staff Computational Materials - MLIPs Engineer at Lam, you will operate on cutting-edge technology, harnessing atomic precision, materials science, and surface engineering to push technical boundaries. Your role involves identifying new and advanced processes and chemical formulations. Your expertise and knowledge will play a crucial role in our customers’ success, making an impact on next generation semiconductor technologies.

• Perform first-principles calculations and atomistic modeling to investigate reaction mechanisms, surface chemistry, plasma-surface interactions, and materials behavior
• Generate high fidelity training datasets from quantum chemistry and density functional theory (DFT) calculations to support development of next-generation simulation capabilities
• Utilize computational chemistry learning to support process engineering research & development, and process/chamber/feature simulations
• Compile and evaluate modeling data to provide guidance on chemistries and materials, as well as appropriate limits and variables for process specifications
• Communicate chemistry and process insights clearly through presentations and technical discussions with stakeholders

• Evaluate machine learning interatomic potential (MLIP) architectures (e.g. MACE, Seven Net)
• Design, train, validate and deploy MLIP architectures using DFT reference data to establish predictive molecular dynamics simulations for various semiconductor device materials and process chemistry applications
• Build scalable workflows for data generation, active learning, model training, uncertainty quantification, and validation of ML-based force fields

• Collaborate with software engineers and domain scientists to integrate MLIP capabilities into simulation platforms and digital twin solutions

• Provide technical leadership in computational materials science, computational chemistry, and machine learning methodologies; mentor engineers and influence cross-functional technology roadmaps
• Drive identification, evaluation, and adoption of emerging simulation and AI technologies that create strategic advantage in semiconductor process development

• Ph.D. in Computational Chemistry, Chemistry, Chemical Engineering or Materials Science (or equivalent)
• 8+ years of industry experience, post Ph.D.
• Experience using DFT software (e.g. Gaussian, Quantum Espresso)
• Experience with frontier molecular orbital analysis and full reaction pathway studies
• Experience applying quantum chemistry fundamentals to solve challenges related to semiconductor processes and materials applications
• Experience developing, training, validating, and deploying MLIP architectures (e.g. MACE, Seven Net)
• Experience with reactive molecular dynamics (e.g. ReaxFF)
• Proficiency in scientific programming using Python, or related languages
• Experience utilizing high performance computing (HPC) environments for large-scale simulations and data analysis
• Demonstrated ability to independently solve complex technical problems and communicate results to multidisciplinary teams
• Strong organizational skills and demonstrated ability to manage multiple tasks simultaneously
• Ability to react to shifting priorities to meet business needs and deadlines

• Experience defining technical strategy for atomistic simulations, machine learning, or scientific computing capabilities
• Experience translating advanced simulation and AI technologies into engineering solutions that impact product development
• Experience leading collaborations with universities, national laboratories, or external technology partners

We believe it is important for every person to feel valued, included, and empowered to achieve their full potential. By bringing unique…