Physics Simulation Engineer

Stand Insurance•San Francisco, CA
•$195,000 - $225,000

About The Position

Stand is building a property-protection platform that uses physics and AI to model catastrophic risk at the individual-property level, automate underwriting, and support mitigation. Its risk engine, the Stand World Model, simulates how catastrophes affect properties and turns those simulations into actionable decisions. As a Physics Simulation Engineer on the Applied Science team, you will build, extend, and improve the physics solvers and their pre- and post-processing workflows for wildfire, wind, flood, and future perils. You will work directly in solver code to add physics, improve runtime, and validate accuracy against experimental and field data. The role involves collaboration with peril subject-matter experts, Machine Learning Engineers, and Platform Engineers to connect simulations across scales, feed probabilistic risk models, and provide data for AI-accelerated surrogates. The position reports to the Physics Simulation Team Lead.

Requirements

  • MS or PhD in mechanical or aerospace engineering, applied mathematics, physics, or a related field.
  • At least 3 years of hands-on simulation development experience.
  • Direct experience modifying solvers—not only running them—in Fortran, C++, or a similar language, and using Python for scripting and tooling.
  • Strong numerical understanding of geometry handling, discretization, convergence, stability, and solver error modes.
  • Depth in CFD and working fluency in structural or FEA modeling, with comfort across heat transfer, fluid flow, structural modeling, and multiphysics coupling.
  • Ability to build automated simulation pipelines that improve reliability, quality, and throughput while reducing human-in-the-loop effort.
  • Track record of validating simulations against experimental or field data with quantified error.
  • HPC experience using parallel workflows with MPI or OpenMP on HPC clusters.
  • Ability to prototype, test, document, and refine quickly under ambiguity, with end-to-end responsibility for solver correctness.
  • Enthusiasm for applying tools and lessons from a current industry in a new setting.
  • Candidates must be authorized to work in the U.S. Stand does not sponsor new work visas; it can consider TN visas, O-1A visas, or H-1B transfers with three or more years remaining.

Nice To Haves

  • Hands-on fluid-structure interaction experience or other coupled multiphysics development.
  • Experience with simulation tools such as Fluent, Siemens Star-CCM+, LS-Dyna, Ansys Workbench, Abaqus, Code_Aster, OpenFOAM, SU2, CalculiX, or Elmer.
  • Experience with multi-objective optimization using custom code or tools such as Pymoo, HEEDS, ModeFrontier, Isight, Optimus, HyperStudy, or Optislang.
  • GPU-accelerated solver experience.
  • Reduced-order modeling, surrogate modeling, or uncertainty quantification experience.
  • Experience building hybrid physics and machine-learning models or working closely with machine-learning engineers on surrogates.
  • Simulation experience applied to natural hazards or risk, such as wildfire, wind, or flood.
  • Startup or zero-to-one experience.

Responsibilities

  • Develop and extend CFD, FEA, and coupled multiphysics solvers to represent phenomena including wave action, combustion, radiation, fire-structure interaction, wind loading, and debris impact.
  • Build automated validation suites and benchmarks to quantify solver error against experimental and field data.
  • Improve parallel solver performance through load balancing, discretization and resolution strategies, and GPU acceleration while maintaining agreed accuracy tolerances.
  • Establish simulation workflows for new perils by gathering requirements, evaluating open-source and commercial solvers, and building preprocessing and solver pipelines.
  • Build coupled multiphysics workflows, including fluid-structure interaction and connections between property-scale solvers and larger-scale peril models.
  • Design simulation campaigns and use reduced-order, surrogate, and uncertainty-quantification methods to turn simulations into probabilistic risk inputs.
  • Document and share knowledge, and teach within and across teams.
  • Support machine-learning surrogate development by generating training data, defining physical constraints and acceptance tests, and integrating surrogates into the simulation pipeline.
  • Work with Platform Engineers on efficient HPC workflows, throughput, and processing costs.
  • Clearly communicate accuracy, runtime, and cost tradeoffs to machine-learning, product, underwriting, and leadership teams.

Benefits

  • Above-market health, dental, and vision coverage.
  • Weekly lunch stipend.
  • Flexible time off and holidays.
  • 401(k) plan.
  • Commuter benefits.
  • Parental leave (PAT & MAT Leave).
  • Short-term and long-term disability coverage.
  • Monthly team gatherings.
  • In-office perks.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service