Staff Software Engineer, AI Inference Cloud

About the role

As an engineer on Arm's AI Inference Cloud team, you will shape the technical direction and develop highly available, scalable services for running AI inference workloads. You will guide architecture and actively contribute to development across Kubernetes orchestration, workload management, service delivery, and observability. Partnering with AI compute, Inference Runtime, and product teams to enhance the performance and usability of Arm's AI platform.

Responsibilities

• Define and build the architecture for cloud-based AI inference services.
• Develop Kubernetes controllers and platform capabilities supporting workload deployment, scheduling, recovery, scaling, upgrades, and lifecycle management.
• Establish production practices for health validation, progressive rollout, rollback, observability, and service objectives.
• Improve platform reliability, scalability, performance, and resource efficiency.
• Lead production readiness reviews and resolve complex issues across services, Kubernetes, networking, and compute infrastructure.
• Turn incidents and operational bottlenecks into durable platform improvements.
• Lead design and build reviews, mentor engineers, and drive technical alignment across teams.

Requirements

• 8+ years of experience, or equivalent proven impact, building distributed systems, cloud platforms, or production infrastructure.
• Deep production experience with Kubernetes, including controllers, operators, scheduling, resource management, networking, and workload lifecycle management.
• Strong software and production engineering skills, including hands-on programming in Go, C++, Rust, Python, or a similar language, and experience with reliable services, APIs, concurrency, observability, deployment safety, capacity planning, and incident response.
• A track record of leading complex technical initiatives while remaining hands-on, including architecture, implementation, debugging, mentoring, and influencing technical direction across teams.
• Ability to troubleshoot complex systems and communicate clearly with engineers from different technical backgrounds.

Preferred qualifications

• Experience with AI infrastructure, model serving, or accelerator-backed workloads.
• Familiarity with frameworks such as PyTorch, Ray, vLLM, SGLang, or TensorRT-LLM, or experience qualifying accelerators and tuning distributed workloads.
• Knowledge of inference performance and resource-efficiency considerations.

Benefits

• Relocation package available, including visa sponsorship support for candidates who require it.
• Total reward package shared during recruitment and selection process (salary is one component).
• Collaborative setting within the AI Platforms team where ideas can come to life quickly.
• Direct impact on Arm's AI inference capabilities and production inference workloads.

Pay

Salary range: $209,100–$282,900 per year.

Schedule

Hybrid working: Arm empowers teams to determine their own hybrid working patterns depending on the work and team needs, balancing face-to-face collaboration with flexibility. Details for each role are shared upon application; flexibility may be limited by local legal, regulatory, tax, or other considerations.