Staff Engineer, Foundation Model Serving & GPU Inference

Databricks; California (MO); On-site; USD 192,000 - 260,000; Full time

Job summary

Databricks is seeking a Staff Engineer to design and build high-throughput, low-latency inference systems for the Foundation Model Serving API. You will shape core infrastructure, influence architecture, and collaborate across platform, product, and research teams to deliver a world-class model serving runtime.

As a senior contributor with 10+ years of distributed systems experience, you will mentor engineers, optimize GPU serving workloads, and help define long-term technical roadmap while

Qualifications

• 10+ years of experience building and operating large-scale distributed systems.
• Experience leading high-scale operationally sensitive backend systems.
• Strong communication skills across fast-moving teams.
• Strategic, product-oriented mindset with ability to align execution with long-term vision.

Responsibilities

• Design and implement core systems and APIs powering Databricks Foundation Model Serving, ensuring scalability and reliability.
• Define the technical roadmap and long-term architecture for serving workloads.
• Drive architectural decisions to optimize performance, throughput, autoscaling for GPU serving workloads.
• Mentor engineers through design reviews and technical guidance and collaborate across product, platform, and research teams.

Job description

Databricks is seeking a Staff Engineer to design and build high-throughput, low-latency inference systems for the Foundation Model Serving API. You will shape core infrastructure, influence architecture, and collaborate across platform, product, and research teams to deliver a world-class model serving runtime.

As a senior contributor with 10+ years of distributed systems experience, you will mentor engineers, optimize GPU serving workloads, and help define long-term technical roadmap while