Senior AI Observability & Reliability Engineer

NVIDIA AI; Santa Clara (CA); On-site; USD 190,000 - 240,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA AI in Santa Clara, CA, seeks a senior software engineer to build observability for agentic AI applications in production. You will collaborate with AI teams to define SLOs/SLIs and lead incident response and reliability improvements for BizApps AI services.

Proficiency in Python, Kubernetes, Docker, Datadog, OpenTelemetry, Grafana, Prometheus, and CI/CD is required. Experience with LangChain, LlamaIndex, Semantic Kernel, Terraform, Pulumi, and GitOps is a plus.

Qualifications

• BS or MS in Computer Science or related field with 8+ years of software engineering experience.
• Hands-on experience with container orchestration and observability platforms.
• Experience in production-grade reliability and incident response.

Responsibilities

• Build and implement observability solutions, including metrics and tracing for agentic AI in production.
• Partner with AI teams to define SLOs/SLIs and drive reliability improvements for BizApps AI services.
• Improve incident response and overall system reliability.

Skills

Python

Kubernetes

Docker

Datadog

OpenTelemetry

Grafana

Prometheus

CI/CD

LangChain

LlamaIndex

Semantic Kernel

Terraform

Pulumi

GitOps

SRE

Distributed Systems

Education

BS or MS in Computer Science

Tools

Kubernetes

Docker

Datadog

OpenTelemetry

Grafana

Prometheus

Terraform

Pulumi

GitOps

Job description

NVIDIA AI in Santa Clara, CA, seeks a senior software engineer to build observability for agentic AI applications in production. You will collaborate with AI teams to define SLOs/SLIs and lead incident response and reliability improvements for BizApps AI services.

Proficiency in Python, Kubernetes, Docker, Datadog, OpenTelemetry, Grafana, Prometheus, and CI/CD is required. Experience with LangChain, LlamaIndex, Semantic Kernel, Terraform, Pulumi, and GitOps is a plus.