jobs

Staff Software Engineer - GenAI inference

P-1285 About This Role As a staff software engineer for GenAI inference, you will lead the architecture, development, and optimization of the inference engine that powers Databricks Foundation Model API.. You’ll bridge research advances and

Company

Databricks

Location

San Francisco, California

Status

Open

Posted

2025-10-08T04:03:51+00:00

Databricks is hiring a staff software engineer to lead the inference engine behind its Foundation Model API. The role covers architecture and optimization across kernels, runtimes, memory, batching and routing, working with researchers to bring new model architectures into production and tuning latency, throughput and GPU utilization. It asks for 6+ years in performance-critical systems, deep knowledge of ML inference internals, CUDA and GPU libraries, and distributed systems design. The posting is onsite in San Francisco with a stated pay range.