Databricks is seeking a Staff Software Engineer to help build and scale the foundation model inference platform that powers enterprise AI workloads. You will develop LLM infrastructure to serve models from partners (OpenAI, Anthropic, Gemini) and self-hosted options (Qwen, GPT-OSS, Llama), focusing on reliability, low latency, and efficiency for large-scale inference. You will collaborate with platform, infrastructure, and ML teams to deliver end-to-end experiences and shape how developers and data scientists interact with AI on Databricks. Requirements include 8+ years in backend or infrastructure engineering, experience with distributed systems, scalable APIs, and cloud-native infrastructure, plus real-time serving, ML infrastructure, or GPU orchestration. Familiarity with service-oriented architecture, deployment pipelines, and observability is expected. Bonus: exposure to SageMaker, Vertex AI, or Azure ML; contributions to OSS projects like MLflow, PyTorch, Ray, vLLM, SGLang; experience building developer platforms or internal AI tooling. This is an on-site role based in San Francisco, California.

Databricks is seeking a Staff Software Engineer to help build and scale the foundation model inference platform that powers enterprise AI workloads. You will develop LLM infrastructure to serve models from partners (OpenAI, Anthropic, Gemini) and self-hosted options (Qwen, GPT-OSS, Llama), focusing on reliability, low latency, and efficiency for large-scale inference. You will collaborate with platform, infrastructure, and ML teams to deliver end-to-end experiences and shape how developers and data scientists interact with AI on Databricks. Requirements include 8+ years in backend or infrastructure engineering, experience with distributed systems, scalable APIs, and cloud-native infrastructure, plus real-time serving, ML infrastructure, or GPU orchestration. Familiarity with service-oriented architecture, deployment pipelines, and observability is expected. Bonus: exposure to SageMaker, Vertex AI, or Azure ML; contributions to OSS projects like MLflow, PyTorch, Ray, vLLM, SGLang; experience building developer platforms or internal AI tooling. This is an on-site role based in San Francisco, California.