Senior Cluster Infra Architect for Frontier AI — Equity

RadixArk; Palo Alto (CA); On-site; USD 200,000 - 400,000; Full time

Job summary

RadixArk is seeking a Member of Technical Staff to architect and scale the core compute platform powering frontier-level AI training and inference. You will design and operate GPU/TPU clusters, build scheduling and resource management systems, and push the limits of large-scale distributed infrastructure for AI workloads.

This role focuses on deep systems engineering across cluster architecture, networking, scheduling, and performance optimization, with impact on how efficiently frontier AI

Qualifications

• 5+ years of experience in distributed systems, infrastructure, or large-scale compute platforms.
• Strong background in distributed systems design and systems architecture.
• Deep experience with cluster management systems (Kubernetes, Slurm, Ray, or custom schedulers).
• Hands-on experience with GPU/TPU infrastructure in production environments.
• Strong Linux systems and networking fundamentals.
• Proficiency in Go, Rust, C++, or Python for production systems.
• Experience debugging complex multi-layer issues across hardware, OS, networking, and distributed services.
• Proven ability to design reliable, scalable systems in production.

Responsibilities

• Architect and scale large AI compute clusters for training and inference.
• Design cluster management, scheduling, and resource allocation systems.
• Optimize performance, utilization, and reliability of GPU/TPU clusters.
• Improve fault tolerance and system resilience at scale.
• Drive observability, monitoring, and performance profiling for cluster infrastructure.
• Collaborate with ML and systems engineers to support frontier AI workloads.
• Lead capacity planning and infrastructure scaling strategies.
• Build internal platforms and tooling to improve developer productivity.
• Document architecture, operational practices, and reliability strategies.
• Contribute to long-term platform vision and technical direction.

Skills

Distributed systems

Cluster management

Kubernetes

Slurm

Ray

Go

Rust

C++

Python

Linux networking

GPU/TPU infrastructure

Production systems

Debugging complex systems

Tools

Kubernetes

Slurm

Ray

Custom schedulers

Job description

RadixArk is seeking a Member of Technical Staff to architect and scale the core compute platform powering frontier-level AI training and inference. You will design and operate GPU/TPU clusters, build scheduling and resource management systems, and push the limits of large-scale distributed infrastructure for AI workloads.

This role focuses on deep systems engineering across cluster architecture, networking, scheduling, and performance optimization, with impact on how efficiently frontier AI