As a Staff Engineer at Databricks, you will play a critical role in shaping the product experience and foundational infrastructure of the Model Serving product. Your focus will be on designing and building systems for high-throughput, low-latency inference across CPU and GPU workloads. You will collaborate with various teams to deliver a world-class serving platform while driving architectural decisions to optimize performance and efficiency. This position requires a strategic mindset and a passion for mentoring engineers.

• 10+ years of experience building and operating large-scale distributed systems.
• Deep expertise in model serving, inference systems, and related infrastructure.
• Strong foundation in algorithms, data structures, and system design.
• Proven ability to deliver technically complex, high-impact initiatives.
• Experience leading architecture for large-scale, performance-sensitive CPU/GPU inference systems.
• Strong communication skills and ability to collaborate across teams.
• Strategic and product-oriented mindset.
• Passion for mentoring and fostering technical excellence.

• Design and implement core systems and APIs for Databricks Model Serving.
• Partner with product and engineering leadership to define the technical roadmap.
• Drive architectural decisions to optimize performance and operational efficiency.
• Contribute to key components across the serving infrastructure.
• Collaborate cross-functionally to translate customer needs into reliable systems.
• Lead technical initiatives that improve latency, availability, and cost-effectiveness.
• Establish best practices for code quality, testing, and operational readiness.
• Represent the team in cross-organizational technical discussions.