Databricks
Senior Staff Software Engineer, AI Runtime
$229K–$343K
Mountain View, California +2 · Senior Staff · Full-time · Posted Oct 22, 2026
- Location
- Mountain View, California
San Francisco, California
San Francisco, California - Experience
- 15+ years in large-scale distributed systems; significant depth in GPU training, high-performance computing, or ML systems.
- Education
- BS in Computer Science or a related field (MS or PhD preferred).
About the job
Leads the architecture and technical direction of Databricks’ AI Runtime, building reliable, efficient infrastructure for large-scale model training.
What you'll do
- Set architecture and long-term technical direction for AI training infrastructure, including reliability, observability, and developer experience.
- Solve multi-node training challenges across orchestration, GPU scheduling, data loading, checkpointing, and performance optimization.
- Align research, product, customer, and engineering teams on priorities, technical trade-offs, and engineering standards.
What they ask for
- 15+ years in large-scale distributed systems, with significant depth in GPU training, high-performance computing, or ML systems.
- Hands-on experience training large models with FSDP, DeepSpeed, or Megatron, and fluency in parallelism strategies.
- Expertise in GPU performance, including accelerator architecture, high-speed interconnects, and kernels.
- Strong understanding of training resilience patterns; experience building multi-tenant cloud platforms and setting technical direction across teams.
Nice to have
- MS or PhD.
Pay
$228,600 — $342,800 USD (salary range)
Tools
FSDP, DeepSpeed, Megatron
AI focus
Build and guide infrastructure for large-scale AI model training, improving reliability, efficiency, and support for new GPU generations and workload types.
Model-written summary · the original posting is authoritative