DatabricksSan Francisco, CAStaff Backend Engineer building and leading the architecture of Databricks Model Serving platform for high-throughput, low-latency AI/ML inference on CPU and GPU. Requires 10+ years large-scale distributed systems experience and deep inference infrastructure expertise.
Staff ML Engineer building CustomerLake, Databricks' Customer Data Platform for enterprise ML/AI personalization, recommendations, churn, and LTV modeling. Requires 10+ years shipping production ML/LLM systems with strong product mindset in 0-to-1 environments.
Designs and builds scalable, low-latency model serving infrastructure for AI/ML models across CPU/GPU workloads. Requires 10+ years in large-scale distributed systems and deep expertise in inference systems, architecture, and cross-team collaboration.
Designs and builds scalable, low-latency systems for serving frontier AI models on GPUs. Requires 10+ years in large-scale distributed systems, strong system design skills, and leadership in operational excellence; no prior AI experience needed.
Designs, implements, and optimizes high-performance GPU kernels for GenAI inference stack. Leads performance improvements, mentors engineers, and collaborates with ML and systems teams. Requires deep kernel programming and GPU architecture expertise.
Leads architecture, development, and optimization of GenAI inference engine for high-throughput, low-latency LLM serving. Requires 6+ years in performance-critical systems, deep ML inference expertise, CUDA/GPU programming, and distributed systems.