Databricks
Senior Software Engineer, Model Serving
$166K–$225K
San Francisco, California +1 · Senior · Full-time · Posted Oct 14, 2025
- Location
- San Francisco, California
Mountain View, California - Experience
- 5+ years building and operating large-scale distributed systems.
About the job
Designs and operates scalable Model Serving infrastructure and APIs for reliable, low-latency AI/ML inference across CPU and GPU workloads.
What you'll do
- Build core Model Serving systems, APIs, deployment workflows, and runtime components.
- Drive architecture and improvements in performance, autoscaling, availability, and cost efficiency.
- Collaborate across teams, establish engineering practices, and mentor engineers.
What they ask for
- 5+ years of experience building and operating large-scale distributed systems.
- Experience in model serving, inference systems, or related infrastructure.
- Strong foundation in algorithms, data structures, and system design for large-scale, low-latency serving.
- Experience building architecture for large-scale, performance-sensitive CPU/GPU inference systems.
Nice to have
Pay
$166,000 — $225,000 USD base salary
Tools
CPU, GPU
AI focus
Build infrastructure for serving traditional ML models and fine-tuned and proprietary large language models, including low-latency inference, monitoring, and autoscaling.
Model-written summary · the original posting is authoritative