Software Engineer - Hosted Model Infrastructure

Palantir

New York, NY, US

This is a role where you'll own real infrastructure problems from end to end. Palantir's customers run AI models in places most engineers never work: air-gapped networks, forward-deployed defense sites, edge nodes with limited GPU. You'll build the systems that make that possible. It's technical, concrete work that directly enables people to do their jobs better.

You'll work across the full stack: inference engines, GPU scheduling, deployment pipelines, observability, and integration with Palantir's platform. You'll treat models like software—continuously tested, continuously delivered, built for reproducibility and long-term maintenance. This means you'll ship real code regularly and see how it gets used.

This fits you if you have strong fundamentals in software engineering, comfort learning systems-level concepts, and curiosity about how ML actually runs in production. You don't need ML expertise—willingness to learn matters more. Computer science or engineering background helps, but shipped projects or solid coursework in systems design work too.

Apply through CareerJumpShip to submit your resume and a brief note on why you're interested in infrastructure work. Palantir will review your application and reach out directly if there's a fit.

About this role

A World-Changing Company Palantir builds the world’s leading software for data-driven decisions and operations. By bringing the right data to the people who need it, our platforms empower our partners to develop lifesaving drugs, forecast supply chain disruptions, locate missing children, and more. The Role We are a software engineering team with expertise in enabling ML models in production. We deploy AI models to run in variety of environments: air-gapped government networks, forward-deployed defense environments, edge nodes, and enterprises with strict data sovereignty requirements. Our customers rely on us for frontier AI capabilities running on hardware they control, often with constrained GPU resources and limited direct access. Rising to that challenge and meeting those expectations is what Palantir's excels at. We treat models like any other software: continuously tested, continually delivered, packaged for reproducible deployment, and built for long-term maintainability. You will own services end-to-end, and work across the full stack, from inference engines, GPU scheduling to deployment pipelines, observability, and integration with Palantir's platform. The goal is to deliver new models and capabilities quickly and continuously. Join us if you want to solve problems at the intersection of infrastructure and machine learning that directly enable critical customers.

Ready to apply?

Similar remote openings sourced directly from company career pages.

Unlock CareerJumpShip

Pick a plan. Start applying.

Every plan unlocks the full product — cancel anytime.

Secured by Stripe · No hidden fees