Simulation Platform Lead

Stand Insurance•San Francisco, CA

2d•$200,000 - $240,000•Onsite

About The Position

As the Applied Science Platform Lead, you’ll lead the platform sub-team within Applied Science that helps build, deploys, and supports Stand’s flagship physics simulations, digital twins, AI/ML models, and spatial intelligence. You’ll own the technical direction, planning, and execution of critical platform initiatives — ensuring they align with Applied Science and companywide stakeholders, ship on schedule, and deliver measurable outcomes. The role spans production AI training and inference, simulation pipelines, infrastructure and CI/CD reliability, geospatial data processing, annotation and QC systems, and new digital-twin capabilities that support Stand’s expansion into new geographies and perils (e.g., hurricane). This is a player-coach role, combining direct technical work with the leadership around it: people management, project planning, cross-team coordination, and process. Reporting to the Chief Science Officer, you’ll own key projects yourself while ensuring the broader sub-team operates effectively, grows, and delivers real impact. You’re the person who looks around corners, sees what the business needs, and turns “the business needs X” into “the team builds Y.” You’ll partner closely with Physics Simulation Engineers, Machine Learning Engineers, and peril-specific SMEs to keep our simulation, AI, and geospatial pipelines reliable, observable, and scalable.

Requirements

Experience leading engineers and technical initiatives, delivering complex projects through others as well as through direct individual contribution.
5+ years building production-grade data, simulation, or modeling pipelines with end-to-end automation, monitoring, and alerting.
Strong project ownership and execution: planning, prioritization, stakeholder coordination, and delivery from concept through production.
Proven ability to debug distributed, data-heavy systems — 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.
Experience with cluster compute and job scheduling (e.g., Slurm and/or Kubernetes) and workflow orchestration (e.g., Prefect or Apache Airflow).
Comfort working across backend, AI pipelines, simulations, and digital twins, even if your background leans toward one area.
Ability to connect technical work to business objectives and customer impact, and to translate SME needs into robust platform capabilities.
Strong, succinct communication, and the judgment to balance research depth, delivery timelines, and business impact.

Nice To Haves

Prior people-management experience, especially in high-growth environments.
Startup or zero-to-one technology development experience.
Experience supporting physics-based or simulation-heavy workflows (e.g., CFD, multiphysics, digital twins) in production, with strong physical-simulation intuition.
Knowledge of geospatial, remote-sensing, or Earth-observation datasets and systems.
Experience working directly with business or product teams on customer-facing technology.
Experience collaborating with MLEs on training pipelines and dataset construction for large-scale models.

Responsibilities

Lead the platform sub-team — set priorities, coordinate execution, and unblock the team to deliver on critical software and infrastructure initiatives.
Manage and grow the team — run 1:1s and growth conversations, give direct and timely feedback, manage performance, and mentor engineers as the team scales.
Design, build, and scale core systems spanning physics simulation, AI, digital twins, computer vision, and spatial intelligence, contributing directly to core components.
Own production pipelines — debug, monitor, and resolve issues to improve uptime and reliability.
Build and support scalable ML infrastructure — data pipelines, training systems, evaluation frameworks, and production monitoring.
Design and operate geospatial pipelines that merge heterogeneous spatial datasets into reproducible, production-grade workflows.
Strengthen CI/CD and infrastructure reliability across simulation, digital-twin, and ML pipelines.
Drive cross-functional alignment and set direction — coordinate across Applied Science and the business, communicate modeling decisions and tradeoffs, and articulate a multi-year vision for how the team’s work moves the business forward.