Software Engineer - Hosted Model Infrastructure

Palantir Palantir · Enterprise · Palo Alto, CA · Dev

Software Engineer focused on enabling ML models in production environments, including air-gapped and resource-constrained settings. The role involves owning services end-to-end, covering inference engines, GPU scheduling, deployment pipelines, and observability, with the goal of delivering new models and capabilities quickly and continuously.

What you'd actually do

  1. 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.
  2. Our customers rely on us for frontier AI capabilities running on hardware they control, often with constrained GPU resources and limited direct access.
  3. We treat models like any other software: continuously tested, continually delivered, packaged for reproducible deployment, and built for long-term maintainability.
  4. 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.
  5. The goal is to deliver new models and capabilities quickly and continuously.

Skills

Required

  • ML model deployment
  • production environments
  • inference engines
  • GPU scheduling
  • deployment pipelines
  • observability
  • full stack development

Nice to have

  • working in air-gapped environments
  • working in defense environments
  • working on edge nodes
  • data sovereignty requirements

What the JD emphasized

  • air-gapped government networks
  • constrained GPU resources
  • limited direct access
  • hardware they control

Other signals

  • deploying AI models in production
  • running in air-gapped government networks
  • constrained GPU resources
  • limited direct access
  • inference engines
  • GPU scheduling
  • deployment pipelines
  • observability