Lead Architect, Runtime at SambaNova Systems

We are currently witnessing the rise of pervasive AI, a shift that allows organizations to leverage generative models to uncover hidden insights, streamline complex processes, and fundamentally transform their operations. At SambaNova Systems, we have developed the SambaNova Suite, which stands as the first full-stack generative AI platform. By integrating everything from our proprietary SN40L chip to advanced software models, we provide enterprise and government clients with a secure, high-performance solution that can be fine-tuned using their own data. We are looking for a Lead Architect, Runtime to join our team and help us build the software infrastructure that powers these sophisticated AI workloads and scientific computing tasks.

Key outcomes

• Lead the architectural design, development, and performance optimization of our runtime software stack to ensure it meets the rigorous demands of AI, machine learning, and HPC applications.
• Create embedded software systems that bridge high-level applications with our hardware, focusing on OS integration, workload orchestration, and fault management.
• Direct the low-level interactions between software and hardware, ensuring efficient chipset initialization and monitoring.
• Define the technical strategy for our Runtime Engineering team, ensuring our software scales effectively with our next-generation Reconfigurable Dataflow Architecture.
• Develop robust tooling and performance profilers that allow our customers to deploy and tune their workloads on our Datascale systems.
• Mentor team members to foster a culture of technical excellence, accountability, and continuous improvement.
• Partner with hardware and product teams to ensure seamless integration across the entire system.

Requirements

• Extensive experience in software engineering, specifically in building and tuning distributed, high-performance systems.
• Deep knowledge of operating systems and runtime stacks.
• Proven expertise in Real-Time Operating Systems (RTOS) and system-level software that interfaces directly with hardware.
• Strong background in High-Performance Computing (HPC) and designing systems for massive parallel workloads.
• A thorough understanding of hardware-software interaction, including registers, device memory management, and accelerator design.
• Proficiency in distributed systems architecture, including networking and communication protocols.
• Experience with development tools such as Git, Jenkins, and Jira to drive automation and continuous integration.
• Professional proficiency in English.

Preferred qualifications

• Experience working with custom hardware accelerators like ASICs or FPGAs.
• Background in deploying high-performance systems within cloud or data center environments.

Compensation

The base salary for this position is between $200,000 and $250,000 per year, depending on your experience, qualifications, and location. In addition to the base salary, we provide a comprehensive total rewards package that includes:

• Equity compensation.
• Medical, dental, and vision insurance.
• Disability insurance.
• Employee assistance program.
• Remote work flexibility.

How to apply

If you are passionate about building the infrastructure that will define the future of AI, we invite you to apply. Please submit an application form for this role through our careers portal to be considered for the position.