Site Reliability Engineer, Cloud

About the role

NVIDIA is seeking an experienced SRE to join its Digital Marketing Organization. The SRE will be responsible for ensuring reliability, speed, and efficiency of all Digital Marketing Services. Key responsibilities include leading and improving AWS Infrastructure, scripting, developing or improving monitoring and alerting tools, and automating deployment pipelines.

Responsibilities

• Quickly identify and categorize user-reported problems within the Digital Marketing Organization ecosystem.
• On-board new applications, AI/ML services, and model endpoints on AWS Infrastructure.
• Implement monitors, alerts, and SOPs to ensure early detection and accurate response to service-impacting issues, including tracking model drift and inference latency.
• Develop and test large-scale dynamic URL redirects using Akamai Edge Redirector Cloudlets for marketing campaigns and site migrations.
• Set up Akamai Forward Rewrite Cloudlets to redirect incoming requests to SEO-friendly URLs.
• Develop, test, and deploy shared and non-shared Cloudlet Policies through the Akamai Cloudlets Policy Manager.
• Maintain custom match criteria — including Geo, Device Characteristics, RegEx, and Query Strings — to guarantee efficient origin offload and intelligent content delivery.
• Provide on-call support for production-grade applications, responding to incidents, prioritizing issues, and driving resolution across deployment pipelines, Akamai CDN, WAF, and cloud infrastructure.

Requirements

• MS or BS in Computer Science/Engineering or equivalent experience with 3+ years of experience supporting technical operations in a live-site production environment.
• Experience building and running critical production services or ML model serving frameworks (e.g., FastAPI, Triton, TorchServe) using Python or Java.
• Strong knowledge of the Kubernetes Platform, deployments, and cloud-native automation.
• Deep familiarity with MLOps frameworks and data pipelines (e.g., MLflow, Kubeflow, Airflow, or AWS SageMaker).
• Advanced level experience with scripting and development in Python, fully automating operational steps with "one-click" rapid solutions.
• Proven strengths in problem-solving and root-causing issues, while continuously seeking ways to drive optimization, efficiency, and the bottom line.
• SRE on-call experience.

Qualifications

• Extensive experience with AWS Cloud Platform and Kubernetes as a platform.
• Hands-on experience deploying and scaling Generative AI/LLM applications, integrating vector databases, or managing GPU-accelerated infrastructure.
• Strong Akamai CDN Support skills and deep understanding of edge computing/edge AI.
• Excellent communication, presentation, and analytical skills; the ability to communicate sophisticated infrastructure and AI concepts clearly across different audiences and varying levels of the organization.

Benefits

Competitive salaries and a generous benefits package are offered. NVIDIA is widely considered to be one of the technology world's most desirable employers. Applications for this job will be accepted at least until July 18, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes. NVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.