Software Architect - SambaStack

About the team

We help enterprises and service providers host their own AI inference platforms, powered by our state-of-the-art RDU (Reconfigurable Dataflow Unit) hardware architecture. Our cloud-agnostic, enterprise-grade inference serving platform enables seamless deployment, management, and scaling of foundation model workloads at production scale.

About the role

As a Software Architect on the SambaStack team, you will define the technical direction of the platform, shaping how it evolves to meet the demands of the world's most demanding enterprise AI workloads. You will own the cross-cutting architectural decisions that span teams and shape the platform's long-term trajectory.

This is a high-impact, high-visibility role at the intersection of:

• AI infrastructure
• Enterprise software
• Systems architecture and design
• Developer experience

Responsibilities

Some of your responsibilities will include:

• Own the end-to-end technical architecture of the SambaStack inference platform, ensuring it meets enterprise-grade standards for scalability, reliability, and performance.
• Define and drive architectural strategy across engineering teams, aligning long-term platform direction with product and business objectives.
• Lead design reviews for major new capabilities and cross-cutting system changes, providing authoritative technical guidance and raising the quality bar across the SambaStack engineering organization.
• Proactively identify and resolve systemic risks, including performance bottlenecks, reliability gaps, and scaling constraints, before they impact customers.
• Establish and evolve architectural standards, patterns, and best practices across the SambaStack engineering organization.
• Partner with ML Engineers, Product Managers, QA, and DevOps to translate complex, ambiguous requirements into sound architectural decisions.
• Serve as a technical thought leader and mentor, growing the architectural thinking and design skills of Software Engineers across the team.
• Evaluate emerging technologies and industry trends to inform the platform's technical roadmap.
• Architect new systems, components, and capabilities to solve new and interesting problems in the AI inference space.

Basic qualifications

• 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: consistency, fault tolerance, observability, and performance at scale.
• Demonstrated experience setting technical direction across multiple teams and driving cross-functional alignment.
• Excellent written and verbal communication skills: Able to clearly articulate complex architectural decisions to both engineering and non-technical audiences.
• Track record of mentoring more junior engineers and elevating team-wide engineering quality.

Preferred qualifications

• 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 (e.g., dataflow architectures, GPUs, 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.
• Experience at a high-growth AI infrastructure company.