Senior Software Engineer, Agentic AI Observability

NVIDIA; Santa Clara (CA); On-site; USD 168,000 - 270,000; Full time

Benefits offered by this job

Equity

Job summary

NVIDIA is seeking a Software Engineer to join the BizApps SRE team, focusing on building observability, deployment pipelines, and reliability for Agentic AI workloads in production. You will collaborate with AI application teams to set SLOs/SLIs and ensure readiness for new agent deployments, while instrumenting LLM workflows for cost and performance monitoring.

Ideal candidates have 8+ years in software engineering with Python, Kubernetes, Docker, and strong debugging skills in distributed

Qualifications

• BS or MS in CS, Software Engineering, or related field (or equivalent).
• 8+ years of experience with strong software engineering in Python and modern CI/CD.
• Hands-on experience with container orchestration (Kubernetes, Docker) and cloud infrastructure.
• Experience with observability/monitoring platforms such as Datadog, OpenTelemetry, Grafana, or Prometheus.
• SRE/DevOps approach - ownership of production systems, automating toil, and reliability focus.
• Excellent problem-solving skills and a proven track record of debugging complex distributed systems.

Responsibilities

• Build and implement observability solutions for agentic AI applications in production, including metrics, tracing, logging, and alerting.
• Develop and sustain deployment pipelines and reliability tools for the Agentic AI Factory model.
• Partner with AI application teams to define SLOs/SLIs and ensure production readiness for new agent deployments.
• Instrument LLM-based workflows for performance, cost, and quality monitoring, covering multi-step reasoning chains, token usage, and tool orchestration.
• Drive incident response, root cause analysis, and reliability improvements for BizApps AI services.
• Identify and close observability gaps outstanding to agentic AI systems, such as hallucination detection and orchestration failure tracing.
• Work jointly with platform, data, and application engineering groups to integrate reliability throughout the development lifecycle.

Skills

Python

CI/CD

Kubernetes

Docker

Observability

SRE/DevOps

Distributed systems debugging

Education

BS or MS in CS/SE or related field

Tools

Datadog

OpenTelemetry

Grafana

Prometheus

Terraform

Pulumi

Job description

NVIDIA is seeking a Software Engineer to join the BizApps SRE team, focusing on building observability, deployment pipelines, and reliability for Agentic AI workloads in production. You will collaborate with AI application teams to set SLOs/SLIs and ensure readiness for new agent deployments, while instrumenting LLM workflows for cost and performance monitoring.

Ideal candidates have 8+ years in software engineering with Python, Kubernetes, Docker, and strong debugging skills in distributed