ML Infra Engineer — Hosted Models & Edge

Palantir; Palo Alto (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

Palantir is seeking a software engineer to join its team focused on enabling machine learning models in production. You will work on deploying AI models across various environments, including government networks and enterprises with strict data sovereignty.

Your work will involve end-to-end service ownership and collaboration across the stack—from inference engines and GPU scheduling to deployment pipelines. If you are interested in tackling infrastructure challenges in machine learning, this role is for you.

Qualifications

• Experience in deploying AI models in various environments.
• Ability to manage end-to-end service ownership.
• Understanding of GPU scheduling and deployment pipelines.

Responsibilities

• Solve problems at the intersection of infrastructure and machine learning.
• Deliver new models and capabilities quickly and continuously.
• Work across the full stack from inference engines to integration.

Job description

Palantir is seeking a software engineer to join its team focused on enabling machine learning models in production. You will work on deploying AI models across various environments, including government networks and enterprises with strict data sovereignty.

Your work will involve end-to-end service ownership and collaboration across the stack—from inference engines and GPU scheduling to deployment pipelines. If you are interested in tackling infrastructure challenges in machine learning, this role is for you.