Staff Software Engineer, Model Serving

<p>At Databricks, we are passionate about enabling data teams to solve the world&39;s toughest problems — from making the next mode of transportation a reality to accelerating the development of medical breakthroughs. We do this by building and running the world&39;s best data and AI infrastructure platform so our customers can use deep data insights to improve their business. </p> <p>Databricks’ Model Serving product provides enterprises with a unified, scalable, and governed platform to deploy and manage AI/ML models — from traditional ML to fine-tuned and proprietary large language models. It offers real-time, low-latency inference, governance, monitoring, and lineage. As AI adoption accelerates, Model Serving is a core pillar of the Databricks platform, enabling customers to operationalize models at scale with strong SLAs and cost efficiency.</p> <p>As a Staff Engineer, you’ll play a critical role in shaping both the product experience and the foundational infrastructure of Model Serving. You will design and build systems that enable high-throughput, low-latency inference across CPU and GPU workloads, influence architectural direction, and collaborate closely across platform, product, infrastructure, and research teams to deliver a world-class serving platform.</p> <p><strong>The impact you will have:</strong></p> <ul> <li>Design and implement core systems and APIs that power Databricks Model Serving, ensuring scalability, reliability, and operational excellence.</li> <li>Partner with product and engineering leadership to define the technical roadmap and long-term architecture for serving workloads.</li> <li>Drive architectural decisions and trade-offs to optimize performance, throughput, autoscaling, and operational efficiency for CPU and GPU serving workloads.</li> <li>Contribute directly to key components across the serving infrastructure — f