Computational Scientist, Structural & Thermal

About Periodic Labs

Periodic Labs is an AI and physical sciences company building state‑of‑the‑art models to accelerate breakthroughs across materials, energy, semiconductors, and beyond. Backed by world‑class investors and growing rapidly, we operate at the pace the frontier requires. Our team brings deep expertise, genuine ownership, and an insatiable drive to push the boundaries of what’s scientifically possible.

Periodic Labs is building AI systems that can simulate physical science, verify predictions, and train on the full scientific method. We are looking for a Computational Scientist to develop structural, thermal, and coupled thermo‑mechanical simulation capabilities for semiconductor systems and advanced materials.

This role is for someone who thinks of themselves as both a scientist and a software engineer. You understand solid mechanics and heat transfer at a level that goes beyond configuring a commercial FEA package, and you are comfortable building, extending, or automating solvers when the physics or scale of the problem requires it.

• Develop agent‑based structural and thermal simulation capabilities for problems central to Periodic Labs’ work: wafer stress and warpage, thin‑film residual stress, thermo‑mechanical reliability, thermal budget modeling, process‑induced deformation, fracture and delamination, and coupled heat‑stress problems in semiconductor structures.

• Build or extend custom solvers where commercial FEA tools are too slow, too opaque, or insufficiently flexible. This may include custom FEM implementations, phase‑field fracture models, crystal plasticity codes, thin‑film mechanics frameworks, or reduced‑order mechanical models, written in Python, C++, or Julia.

• Model materials behavior at the level the physics requires: elasticity, plasticity, viscoelasticity, creep, fracture, diffusion‑induced stress, thermal expansion mismatch, interfacial mechanics, and materials evolution under process conditions.

• Couple structural models to thermal, fluid, or chemical physics as the problem demands.

• Validate models against experimental measurements including wafer metrology, curvature and bow measurements, DIC, profilometry, nanoindentation, or failure analysis data.

• Design and curate evaluation datasets in collaboration with RL researchers to train LLMs capable of directing complex simulation pipelines.

• Generate simulated datasets for ML training in regimes where experimental coverage is expensive or difficult to achieve.

• Build and automate simulation pipelines  just setting up individual runs, but architecting workflows that connect simulation outputs to data infrastructure, ML systems, and autonomous experimentation loops.

• Integrate mechanics and thermal models into Periodic Labs’ AI‑driven workflows so that simulations become active tools for process optimization and engineering decision‑making.

• Periodic Labs is an early‑stage startup, and we’re looking for someone who can bring technical leadership to modeling structural and thermal behavior in semiconductor devices, not necessarily someone who already has every skill listed below. A strong growth mindset, demonstrated ownership, and a track record of getting up to speed quickly in new technical areas are more important than experience in semiconductors.

• A PhD or equivalent research experience in mechanical engineering, materials science, aerospace engineering, or a closely related field, with a strong foundation in solid mechanics and heat transfer. Strong early‑career candidates with a demonstrated upward trajectory are encouraged to apply.

• Hands‑on experience with computational mechanics at the code level: writing or substantially modifying FEM codes, implementing constitutive models, or developing custom solvers for structural or thermal problems.

• Familiarity with open‑source simulation frameworks such as FEniCS, deal.
  
  II, MOOSE, or similar is a strong positive signal. Contributions to open‑source projects that others actually use are even better.

• Strong Python skills. Proficiency in C++ is a plus. Experience running simulations programmatically at scale, not just…