Senior Agentic AI Kernel Engineer

NVIDIA; United States; On-site; USD 184,000 - 357,000; Full time

Job summary

NVIDIA in the United States is seeking a senior software engineer to build agentic AI systems that operate directly on GPU software artifacts, owning end-to-end lifecycle from prototype to deployment and continuous improvement.

You will develop robust LLM-powered pipelines for code generation, automated bug triage, regression detection, and intelligent test coverage analysis, while collaborating with GPU SW kernel engineers to convert domain knowledge into scalable automation.

Qualifications

• BS/MS in Computer Science, Computer Engineering or equivalent experience
• 8+ years of software engineering experience including 2+ years in production LLM/agentic AI systems
• Strong Python skills and experience with LangChain/LlamaIndex or equivalent
• Hands-on with RAG pipelines, tool-use/function-calling, multi-step agentic services
• Proven experience delivering agentic AI in live production
• Solid software engineering fundamentals: build, test, observability, scalable architecture
• Strong analytical skills: precision/recall, false positives, evaluation methods

Responsibilities

• Own full lifecycle of agentic services from prototype to deployment and improvement
• Build LLM-powered pipelines for code generation, bug triage, regression detection, and test coverage analysis
• Develop agentic knowledge layer and MCP-based infrastructure to interface with 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

Job description

NVIDIA in the United States is seeking a senior software engineer to build agentic AI systems that operate directly on GPU software artifacts, owning end-to-end lifecycle from prototype to deployment and continuous improvement.

You will develop robust LLM-powered pipelines for code generation, automated bug triage, regression detection, and intelligent test coverage analysis, while collaborating with GPU SW kernel engineers to convert domain knowledge into scalable automation.