Machine Learning Engineer - Multimodal Modeling

About the role

Why Join Stand https://www.standinsurance.com/careers/why-stand/: At Stand, you’ll help build a new class of global property protection. We use advanced physics and AI to model catastrophic risk at the asset level, then automate underwriting and mitigation before loss occurs. Insurance is simply the current delivery mechanism. The real product is a scalable risk engine, our Stand World Model https://frontier.standinsurance.com.

We stay when traditional insurers exit. We model what others approximate. And we build systems that change outcomes, not just prices.

Our leadership team https://www.standinsurance.com/vision has built category-defining companies (Metromile, Policygenius, WePay, HotelTonight) and brings decades of expertise in underwriting, capital management, and reinsurance.

Background: The property insurance industry is built to price loss after it happens. It relies on coarse proxies, backward-looking data, and manual processes, then accepts damage as unavoidable.

Stand takes a different approach. We simulate how real-world catastrophes affect individual properties, translate that into actionable decisions, and automate the business around it. The result is a platform that can underwrite what others can’t and operate with far less friction.

Role Summary:

As a Machine Learning Engineer on the Applied Science team, you will design, train, and deploy Stand's flagship AI capabilities, with a central focus on the multimodal meshing of our Stand World Model with powerful language models. This work brings physical simulation, rich 3D representations of real assets, and broader business context together into models that can reason across all of them at once, in support of better underwriting, pricing, and mitigation decisions.

This is a hands-on, high-ownership position on the Machine Learning team within Stand Applied Science. You will own modeling work end-to-end, from architecture and training strategy through evaluation and production deployment, and partner closely with the Platform team to ensure the agentic harness and workflows your models plug into deliver strong results in production.

Your partnerships will extend across the business, mirroring the breadth of the model's inputs: collecting technical insight from subject matter experts and other MLEs, and institutional judgment from underwriting, pricing, mitigation, inspection, and customer decision-making.

Key initiatives include:

- Designing and training multimodal model architectures that jointly reason over physical, spatial, and business-context data

- Building frameworks that let these models act as agents within nuanced workflows, making complex tool calls that include interacting with our world-modeling stack

- Developing retrieval and similarity capabilities over learned representations of real-world assets and their multi-layered complexities

- Standing up the training-data pipelines, evaluation harnesses, and production monitoring that take these models from prototype to production, collaborating closely with Applied Science infrastructure engineers to build out proper tooling