Agentic AI Kernel Engineer — GPU Automation

NVIDIA; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Job summary

NVIDIA's GPU SW Kernel organization is seeking an experienced software engineer to build agentic AI systems that operate on GPU software artifacts, including source code, crash dumps, changelists, test results, and CI/CD signals. You will own the end-to-end lifecycle of agentic services from prototype to deployment and continuous improvement.

The role requires 8+ years in software engineering, strong Python, and hands-on experience with LLM frameworks and RAG pipelines.

Qualifications

• BS/MS in Computer Science, Computer Engineering, or equivalent experience.
• 8+ years of software engineering experience, including a minimum of 2 years developing production LLM or agentic AI systems.
• Strong Python skills and experience with modern LLM frameworks (LangChain, LlamaIndex, or equivalent).
• Hands-on experience with RAG pipelines, tool-use / function-calling patterns, multi-step agentic services, and timely engineering at scale.
• Solid software engineering fundamentals: system build, testing, observability, and scalable architecture.
• Strong analytical skills — comfortable reasoning about precision/recall tradeoffs, false positive rates, and evaluation methods for agent outputs.

Responsibilities

• Own the full lifecycle of agentic services: from prototype through evaluation, deployment, and continuous improvement
• Build robust LLM-powered pipelines for code generation, automated bug triage, regression detection, and intelligent test coverage analysis
• Develop the agentic knowledge layer and MCP-based infrastructure that allow agents to interact with internal developer systems (Gerrit, NVBugs, CI/CD, Perforce, Slack)
• Design and assess agent quality thoroughly — establish metrics, develop evaluations, measure precision/recall tradeoffs at each stage of the funnel
• Work closely with GPU SW kernel engineers to pinpoint high-impact automation opportunities and convert domain knowledge into effective agentic AI systems
• Drive adoption across GPU SW teams by shipping agentic services that are fast, reliable, and meaningfully better than the manual alternative!

Skills

Python

LLM frameworks

Agentic AI

RAG pipelines

Education

BS/MS in Computer Science or related field

Tools

LangChain

LlamaIndex

Gerrit

NVBugs

CI/CD

Perforce

Job description

NVIDIA's GPU SW Kernel organization is seeking an experienced software engineer to build agentic AI systems that operate on GPU software artifacts, including source code, crash dumps, changelists, test results, and CI/CD signals. You will own the end-to-end lifecycle of agentic services from prototype to deployment and continuous improvement.

The role requires 8+ years in software engineering, strong Python, and hands-on experience with LLM frameworks and RAG pipelines.