Software Architect - San Jose, California, United States

Originally posted 2 June 2026 by the employer.

Architect the SambaStack enterprise inference serving platform for Reconfigurable Dataflow Unit (RDU) hardware.

About the role

As a Software Architect on the SambaStack team, you will define the technical direction of the cloud-agnostic enterprise inference serving platform and own cross-cutting architectural decisions across teams. The platform powers AI inference deployments using SambaNova's Reconfigurable Dataflow Unit (RDU) hardware architecture.

What you'll do

- Own the end-to-end technical architecture of the SambaStack inference platform across scalability, reliability, and performance. - Define architectural strategy across engineering teams, aligning platform direction with product and business goals. - Lead design reviews for new capabilities and cross-cutting system changes, providing technical guidance across the organization. - Proactively identify and resolve systemic risks including performance bottlenecks, reliability gaps, and scaling constraints. - Establish and maintain architectural standards, patterns, and best practices across the SambaStack engineering team. - Partner with ML Engineers, Product Managers, QA, and DevOps to translate complex requirements into architectural designs.

What you'll need

- 12+ years of software engineering experience, including significant time in a role with organization-wide technical influence. - Proven track record of owning large-scale distributed systems architectures end-to-end from design to production. - Expertise building backend systems in Python, Go, or Rust. - Expert-level understanding of Kubernetes, including Operators, Helm Charts, and cluster-scale resource management. - Strong command of distributed systems principles, including consistency, fault tolerance, observability, and performance at scale. - Demonstrated experience setting technical direction across multiple teams and driving cross-functional alignment.

Nice to have

- Deep familiarity with AI inference serving, orchestration, and the infrastructure challenges of LLM workloads at production scale. - Experience designing systems for custom or novel hardware accelerators such as dataflow architectures, GPUs, or TPUs. - Background in ML application optimization and productionization. - Experience building cloud-native platforms for enterprise customers with stringent SLA and compliance requirements. - Familiarity with AI coding assistants and the developer tooling ecosystem.

Skills: AI inference platform, systems architecture, Kubernetes, distributed systems, scalability, Python