Senior Staff Infrastructure & Site Reliability Engineer – AI Datacenter

About the role

The role focuses on configuring, operating, and continuously improving large‑scale AI inference systems in a datacenter environment. You will ensure Qualcomm’s AI infrastructure is reliable, scalable, and production‑ready for advanced machine‑learning workloads.

Key responsibilities

• Define and apply best‑practice configurations, deploy, and operate large‑scale AI inference systems supporting critical AI workloads.
• Ensure reliability, availability, and scalability of AI datacenter clusters.
• Develop and maintain software tools and support infrastructure around AI software stacks.
• Collaborate with hardware and architecture teams to support AI workloads, including LLM inference and agentic AI workflows.
• Apply SRE fundamentals: monitoring, alerting, incident response, and performance optimization.
• Maintain observability tools, dashboards, and alerts using Prometheus, Grafana, CloudWatch, and custom telemetry.
• Automate operational tasks and support CI/CD pipelines for AI services using Infrastructure‑as‑Code tools such as Terraform and Ansible.

Required profile

• 8+ years of experience in Site Reliability Engineering or related infrastructure roles.
• Strong background in AI/ML workloads, including LLMs, NLP, vision, audio, or recommendation systems.
• Hands‑on experience with AI inference concepts such as batching, token streaming, and performance tuning.

Required skills

• PyTorch and modern ML frameworks
• Prometheus, Grafana, CloudWatch
• Terraform, Ansible
• CI/CD pipeline development
• Infrastructure‑as‑Code practices