Computational Scientist, Differentiable Physics

About the role

Periodic Labs is developing AI systems that can simulate physical science, verify predictions, and train on the full scientific method. We seek a Computational Scientist to create differentiable, accelerator‑ready simulations for industrially relevant continuum‑physics problems.

Key responsibilities

• Build and extend differentiable solvers for continuum simulation, including fluid dynamics, multi‑scale and multi‑physics problems.
• Implement numerical methods from equations and research papers, diagnosing convergence, stability, and modeling failures.
• Combine simulation with deep learning for surrogate modeling, learned physics, inverse problems, parameter estimation, and optimization.
• Use automatic differentiation and modern accelerators (JAX or PyTorch) to make simulations scalable and trainable.
• Validate models against experiments, trusted benchmarks, or high‑fidelity simulations.
• Create datasets and evaluation suites to guide the development of LLMs that accelerate and automate these tasks.

Required profile

• PhD or equivalent research experience in applied mathematics, computational science, physics, engineering, computer science, or a related field.
• Code‑level experience building or substantially modifying PDE solvers, numerical methods, or differentiable simulations.
• Deep expertise in at least one continuum domain with the ability to learn new physics quickly.
• Experience building, training, and evaluating deep‑learning models for physical systems.
• Strong Python and software‑engineering skills, especially with JAX, PyTorch, Julia, or C++.
• Track record applying simulation to realistic scientific or engineering problems, not only academic benchmarks.
• Startup mentality: ownership, good judgment under uncertainty, and enthusiasm for building from scratch.

Required skills

• Python
• JAX
• PyTorch
• Julia
• C++
• Automatic differentiation
• GPU acceleration
• TPU acceleration
• PDE solvers
• Numerical methods
• Deep learning for physical systems

What we offer

• Compensation: $250,000‑350,000 per year plus equity
• Visa sponsorship
• Location in Menlo Park, CA (future expansion to San Francisco)
• Opportunity to work on cutting‑edge AI for scientific discovery in a fast‑moving startup environment