Summer 2027 - Process Simulation Engineering Intern - MS/PhD

Lam Research•Fremont, CA

1d•$30 - $48•Hybrid

About The Position

As a Process Simulation Engineering Intern in the Office of the CTO, you will help build a virtual twin of plasma etch processes. You will develop physics-based models of plasma etching and fast machine-learning surrogate models that connect tool settings to predicted feature profiles. The work supports data-driven process development for Lam’s etch products. The position is an onsite-flex role, with at least three days per week onsite. The internship includes documenting the workflow and presenting results at its conclusion.

Requirements

Currently pursuing an MS or PhD in chemical engineering, physics, materials science, chemistry, or a related field.
Strong Python skills, including hands-on experience building and training models in PyTorch or a similar framework such as JAX or TensorFlow.
Background in reaction kinetics, transport phenomena, or surface/plasma science.
Hands-on experience building machine-learning or regression models.
Strong analytical and communication skills, and ability to work effectively in a team.

Nice To Haves

Coursework or research in plasma physics or plasma-surface interactions.
Experience with surrogate modeling methods such as Gaussian processes, neural networks, polynomial chaos, or reduced-order models.
Experience with GPyTorch/BoTorch, physics-informed neural networks, or uncertainty quantification.
Experience with design of experiments, sensitivity analysis, Bayesian calibration, or optimization.
Experience with physics-based simulation tools such as finite element, Monte Carlo, or feature-scale/profile simulators.
Familiarity with semiconductor etch processes or SEM/TEM image analysis.

Responsibilities

Build and refine models of plasma etching, including ion and neutral species interactions with wafers, sticking and reaction probabilities, redeposition, and ion energy and angle effects.
Calibrate model parameters against measured profiles, such as critical dimension versus depth from SEM/TEM images.
Design simulation experiments, including parameter sweeps and design of experiments, to generate training data.
Build and validate fast surrogate models of slower physics simulations, including evaluating accuracy and uncertainty.
Use surrogate models to identify influential settings and optimize process conditions.
Write Python tools to automate simulation runs, data processing, and plotting.
Document the workflow and present results at the end of the internship.