Principal Software Engineer, Runtime

The Runtime Team at SambaNovaThe Runtime team is at the core of SambaNova’s technology stack. We specialize in delivering high-performance system software solutions that power AI and machine learning applications across the enterprise landscape. Our team operates at the lowest levels of the SambaNova stack, directly above the hardware, and is responsible for all aspects of infrastructure that support the higher-level applications.Our work includes:OS integration and interface managementData model manipulation to ensure scalabilityIntra- and inter-node networking/communicationOrchestration of partitioned workloadsError monitoring and general hardware lifecycle managementWe build a distributed, scalable, and high-performance software environment that supports data-driven applications such as ML training and inference, ETL data processing, and high-performance computing (HPC) applications.The Role: Software Engineer – Runtime InfrastructureWe’re looking for an experienced Software Engineer to join our Runtime team and help us continue to build, optimize, and scale the infrastructure that powers SambaNova’s generative AI solutions. In this role, you’ll work on a diverse range of technologies, from low-level drivers and kernel modules to high-level user-space libraries. You will play a crucial role in shaping the next generation of high-performance compute systems for AI applications at scale.As a key member of our team, you’ll have the opportunity to:Design and enhance the infrastructure for ML training and inference at scale.Support system software, including drivers and kernel modules, for cutting-edge hardware.Build user-facing tools that improve system monitoring, job management, and profiling for the SambaNova platform.Develop solutions for virtualization and multi-tenant environments to improve ease of use and isolation.Collaborate with cross-functional teams, including ML, Compiler, and DevOps, to ensure system-wide optimization.What We’re Looking For:Strong experience in operating system development, including kernel space drivers and user-space libraries.Expertise with communication fabrics (e.g., RDMA, PCIe, Infiniband, RoCE) and high-performance data transport mechanisms.Hands-on experience with software bring-up for custom hardware platforms.A solid understanding of distributed systems, performance tuning, and large-scale system architecture.Excellent problem-solving skills and the ability to work collaboratively in a fast-paced, dynamic environment.Strong communication skills and a passion for mentoring and working with colleagues across teams.Preferred Skills & Qualifications:Familiarity with high-performance computing (HPC) workloads and AI applications.Experience with containerization and virtualization technologies.A track record of contributing to open-source projects or developing innovative system-level software.Enthusiasm for innovation and the drive to push the boundaries of what’s possible in the world of AI.At SambaNova, we are building the future of AI, and we want you to be part of that journey. If you’re ready to work on groundbreaking technology and make a lasting impact, we’d love to hear from you.Annual Salary Range and LevelThe base salary for this position ranges from $170,000/year up to $210,000/year. This range is based on role, level, and location and reflects the salary target for new hires in the US. Individual pay within the range will depend on a number of factors, including a candidate’s job-related qualifications, skills, competencies and experience, and location. #J-18808-Ljbffr

Created: 2025-09-17