Software Engineer- BIS (Baseten Inference Stack)

About this role

Join Baseten's Inference Stack team to build the distributed runtime powering large-scale LLM inference. You'll work across the full stack—from developer tools to Kubernetes orchestration—enabling AI companies to deploy cutting-edge models with industry-leading performance and reliability.

What you'll do

• Develop infrastructure and orchestration systems for distributed LLM inference at scale
• Build platform capabilities for routing, autoscaling, scheduling, observability, and runtime management
• Work across the stack from customer-facing features to low-level infrastructure components
• Collaborate with Model Performance engineers to make inference optimizations accessible and configurable
• Debug complex production systems spanning Kubernetes, distributed runtimes, networking, and GPU workloads
• Own end-to-end projects from architecture through deployment and iteration based on customer feedback

What they're looking for

• Distributed systems and backend infrastructure
• Platform engineering and production systems
• Kubernetes and container orchestration
• Debugging across multiple stack layers
• Developer experience design
• GPU workload management
• Willingness to learn new languages and frameworks
• Strong communication and collaboration

Benefits

• Work on mission-critical inference powering leading AI companies like Cursor and Notion
• Recently raised $1.5B Series F with top-tier investors
• Located in San Francisco
• Opportunity to own systems in production
• Cross-functional collaboration with Model Performance teams
• Impact on frontier AI infrastructure