Agentic AI Kernel Engineer — Drive GPU Automation

NVIDIA Gruppe; Santa Clara (CA); Hybrid; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a senior engineer to build agentic AI systems operating on GPU software artifacts, including source code, crash dumps, and CI/CD signals.

You will own the full lifecycle of agentic services, build LLM-powered pipelines, develop the MCP-based infrastructure, and define robust evaluation metrics. Collaboration with GPU SW kernel engineers will be essential to deliver high-impact automation.

Qualifications

• BS/MS in Computer Science, Computer Engineering, or equivalent experience.
• 8+ years of software engineering experience.
• 2+ years developing production LLM or agentic AI systems.
• Strong Python skills and experience with modern LLM frameworks.
• Hands-on experience with RAG pipelines and multi-step agentic services.
• Proven experience delivering agentic AI in live production.
• Solid software engineering fundamentals.

Responsibilities

• Own the full lifecycle of agentic services from prototype to deployment.
• Build robust LLM-powered pipelines for code generation, bug triage, regression detection, and test coverage analysis.
• Develop agentic knowledge layer and MCP-based infrastructure for internal systems (Gerrit, NVBugs, CI/CD, Perforce, Slack).
• Design and evaluate agent quality with metrics and tradeoff analyses.
• Collaborate with GPU SW kernel engineers to identify automation opportunities.
• Drive adoption by shipping fast, reliable agentic services superior to manual processes.

Skills

Python

LLM frameworks

RAG pipelines

Agentic AI systems

Production deployment

Software fundamentals

Analytical skills

Education

BS/MS in CS/CE or equivalent

Tools

Gerrit

NVBugs

CI/CD

Perforce

Slack

Job description

NVIDIA is seeking a senior engineer to build agentic AI systems operating on GPU software artifacts, including source code, crash dumps, and CI/CD signals.

You will own the full lifecycle of agentic services, build LLM-powered pipelines, develop the MCP-based infrastructure, and define robust evaluation metrics. Collaboration with GPU SW kernel engineers will be essential to deliver high-impact automation.