Senior Staff Site Reliability Engineer

Define the architecture and technical roadmap for a scalable enterprise AI runtime platform.

Design Kubernetes-based systems for deploying, running, and scaling AI applications, inference services, and databases.

Build control-plane services, APIs, operators, and automation for workload provisioning, configuration, upgrades, and recovery.

Develop runtime capabilities for GPU scheduling, autoscaling, load balancing, and rate limiting.

Improve the performance, availability, and developer experience of large-scale AI inference services.

Build and automate relational and vector database services, including provisioning, scaling, backup, and failover.

Establish secure and consistent application lifecycle-management patterns spanning cloud-based and on-premises platforms.

Develop observability tools for monitoring, profiling, and debugging applications, GPU resources, inference workloads, and databases.

Lead technical initiatives across multiple functions, mentor engineers, and establish standards for the platform’s long-term evolution.

BS, MS, or PhD in Computer Science, Engineering, or a related field—or equivalent experience.

8+ years of software engineering experience building distributed systems, cloud infrastructure, database platforms, or large-scale backend services.

Strong programming skills in Python, Go, C++, or Java, with experience delivering production-grade systems.

Proven track record designing scalable and highly available Kubernetes-based platforms and leading technical strategy, influence across teams, and tackle complex platform problems.

Experience building control planes, platform APIs, Kubernetes operators, or workload lifecycle-management systems.

Experience developing high-performance services for AI inference or other low-latency workloads.

Practical knowledge of relational or vector databases, including availability, replication, query optimization, and performance tuning.

Experience with GitOps, CI/CD, observability, and cloud-native security practices.

Experience building self-service platforms for application and infrastructure lifecycle management.

Experience with inference-serving frameworks, GPU-aware scheduling, or model-performance optimization.

Expertise in vector databases, GPU-accelerated query engines, or distributed data platforms.

Experience supporting the complete AI application lifecycle, from development through production serving and monitoring.

Contributions to open-source projects in Kubernetes, AI/ML infrastructure, databases, distributed systems, or observability.

NVIDIA is committed to encouraging a diverse 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.

Widely considered to be one of the technology world’s most desirable employers, NVIDIA offers highly competitive salaries and a comprehensive benefits package. As you plan your future, see what we can offer to you and your family www.nvidiabenefits.com/