Simulation Platform Engineer

Stand Insurance•San Francisco, CA

2d•$180,000 - $210,000

About The Position

Stand is a new technology and insurance company revolutionizing how society assesses, mitigates, and adapts to climate risks. Our leadership team has extensive experience in insurance, technology, and climate science: building billions in market value at prior ventures. At Stand, we are rethinking how insurance enables proactive, science-driven resilience. Existing insurance models often rely on broad exclusions, leaving homeowners without options. At Stand, we leverage advanced deterministic models and cutting-edge analytics to provide personalized risk assessments—helping homeowners secure coverage and take proactive steps toward resilience. Why Join Stand: At Stand, you’ll join a mission-driven team redefining insurance through the lens of climate resilience, building a transformative, data-driven insurance model with real-world impact for homeowners and communities on the front lines of climate change. The Opportunity: The Simulation Platform Engineer owns and extends the simulation and digital twin platform that underpins Stand’s modeling workflows. This role spans production simulation pipeline development and support, infrastructure and CI/CD reliability, geospatial data processing, annotation and QC systems, and the development of new digital twin capabilities to support the expansion of the business into new geographies and perils, e.g., hurricane. You will work closely with Physics Simulation Engineers, Machine Learning Engineers, and peril-specific SMEs to ensure our simulation, AI, and geospatial pipelines are reliable, observable, and scalable. This position is ideal for someone who thrives in fast-paced environments, owns outcomes end to end, collaborates effectively across disciplines, and is energized by building from zero to one.

Requirements

5+ years of hands-on experience building and maintaining production-grade data, simulation, or modeling pipelines, with end-to-end automation, monitoring, and alerting.
Proven ability to debug distributed, data-heavy systems, especially those spanning APIs, preprocessing, modeling, and downstream consumers.
Hands-on experience with cloud infrastructure and CI/CD, including infrastructure-as-code, automated testing, and reliable deployment practices.
Comfort working at the intersection of simulation, digital twins, and ML, even if your background leans more heavily toward one area.
Experience designing reproducible workflows, with versioned datasets, scripted transformations, and auditable pipelines.
Ability to collaborate directly with simulation engineers, MLEs, and domain SMEs, translating modeling needs into robust platform capabilities.
High ownership and operational rigor, treating pipelines and platforms as long-lived products, not one-off projects.
Bachelor’s or Master’s degree in Computer Science, Engineering, Applied Mathematics, Physics, or a related technical field.
Highly self-motivated, with a “run-through walls to get the problem solved” method, self-directed, proactive, and adaptable;, comfortable operating in fast-paced, ambiguous environments where problems, interfaces, and priorities evolve over time.

Nice To Haves

Experience supporting physics-based or simulation-heavy workflows (e.g., CFD, multiphysics, or digital twin systems) in production, with strong physical simulation mathematical intuition.
Hands-on experience with geospatial data stacks, including LiDAR, DEMs, and digital twin manipulation.
Experience working directly with business units or product teams on customer or client-facing technology.
Experience collaborating with MLEs on training pipelines and dataset construction for large-scale models.
Proven ability to operate effectively in startup environments, balancing rapid delivery with long-term platform reliability and high ownership.

Responsibilities

Own and support production simulation pipelines, debugging, monitoring, and resolving issues across wildfire simulation and related workflows to improve uptime and MTTR.
Strengthen CI/CD and infrastructure reliability across simulation, digital twin, and ML pipelines through automated testing, safe deployments, and compute efficiency.
Build and operate annotation and QC systems for digital twins, improving quality and reducing manual effort via ML-assisted workflows.
Develop digital twin capabilities, including multiphysics-adjacent features for wind, flood, and other perils.
Integrate new peril pipelines end to end, across multiple scales, connecting preprocessing, vendor and geospatial data, simulation workflows, and post-processing modules.
Partner with MLEs on AI pipelines, supporting training, inference, and continuous improvement (e.g., FireNet).
Design and operate geospatial pipelines, merging heterogeneous spatial datasets into reproducible, production-grade workflows.
Communicate clearly across teams on pipeline stability, data quality, and failures to enable fast iteration.