About the job
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.
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.
Qualifications
Minimum
Bachelor’s in Computer Science, Computer Engineering, or equivalent and with 3-5 years of industry experience
Proficiency in C/C++ and Python
Experience with user space libraries, operating systems, and kernel drivers
Experience working with highly concurrent and distributed systems, with a focus on performance and scalability
Preferred
Experience with different types of fabrics, such as PCIe, Infiniband, and RoCE
Experience with fast networking stacks, such as RDMA
Good communication skills and enthusiasm to help colleagues