Runtime Engineer

SambaNova is a leader in next-generation AI infrastructure, delivering a full-stack inference platform for customers worldwide. At the core of SambaNova's technology is the RDU (Reconfigurable Dataflow Unit) — a chip built on a dataflow architecture rather than the traditional GPU model. Its decode performance is especially strong for agentic workloads like multi-turn agents, code generation, and long-running applications. RDUs are packaged into SambaRack, rack-scale hardware that lets customers deploy state-of-the-art models with better performance, greater energy efficiency, and faster time to value.

About the role

The Runtime team at Sambanova is a seasoned engineering team with a proven track record of delivering cutting-edge system software solutions for AI and machine learning applications in the enterprise & commercial landscape.

Runtime is responsible for the lowest levels of the SambaNova stack, efficiently interacting with the hardware to provide the best application performance and maximize hardware utilization. We handle all aspects of software infrastructure to enable higher level applications, including:

• High performance user libraries
• Operating System interface/integration
• Data model manipulation for scaling
• Networking/communication intra and inter node
• Orchestration of partitioned workloads
• Error monitoring and tools for system management and observability

We build a high performance, distributed and scalable software execution environment for SambaNova DataScale & Cloud platforms to support data-flow applications such as ML training and inference and HPC applications.

We are searching for a software engineer who will work on all parts of the runtime stacks, supporting AI, ML, and scientific applications in high-performance distributed systems. You will participate in building, testing and deploying next-generation high-performance compute systems for AI applications at scale. We expect the candidate to have a strong background in programming, building and testing software in distributed systems, performance tuning of large scale systems, and good teamwork and planning skills.

Responsibilities

• Work on design and implementation of new and enhanced features of the runtime stack to support high performance and scalable ML inference and training applications
• System software (drivers and kernel) support for the next generation silicon.
• Design user-space libraries for high performance and high utilization of HW resources.
• User-facing tools (analysis, job and HW management, profiling, debugging, etc) for Datascale systems.
• Collaborate with other teams including Hardware, ML Application, Compiler, DevOps.