Skip to main content

Palantir

Software Engineer - Hosted Model Infrastructure

New York, NYfull-timemidAdded 1 month ago

About this role

Palantir seeks a Software Engineer to build and maintain infrastructure for deploying AI models across diverse environments, from air-gapped networks to edge devices. You'll own end-to-end services spanning inference engines, GPU scheduling, deployment pipelines, and observability, ensuring models run reliably on customer-controlled hardware with limited resources.

What you'll do

  • Design and maintain ML model deployment infrastructure for restricted environments
  • Develop and optimize inference engines and GPU resource scheduling systems
  • Build deployment pipelines and observability solutions for production models
  • Integrate hosted model services with Palantir's broader platform
  • Ensure continuous testing and delivery of model updates
  • Support customers running AI on constrained hardware in air-gapped networks

What they're looking for

  • Software engineering and full-stack development
  • Machine learning infrastructure and model deployment
  • GPU scheduling and optimization
  • Cloud/edge computing and distributed systems
  • DevOps, CI/CD pipelines, and observability tools
  • Data systems and platform integration
  • Problem-solving in resource-constrained environments
  • Python or systems programming languages
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

Palantir

Palantir builds data platforms and software solutions that help government and enterprise customers tackle complex operational challenges, with a focus on responsible AI governance and privacy. The company is hiring software engineers and interns for forward-deployed customer roles, infrastructure and platform teams, and specialized privacy and civil liberties engineering positions.

View all jobs at Palantir

Likely interview questions

  • Walk us through your experience deploying ML models to production. What were the biggest infrastructure challenges you faced, and how did you solve them?
  • How have you approached packaging and versioning ML models for reproducible deployment across different environments?