Agentic AI Systems Engineer — GPU Kernel (Equity)

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

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA Corporation in Santa Clara, CA invites applications for a senior role shaping agentic AI systems that operate directly on GPU software artifacts. You will build end-to-end pipelines for code generation, bug triage, and regression coverage, while driving automated, scalable AI solutions across GPU software teams.

The role demands 8+ years in software engineering with production LLM experience, strong Python, and familiarity with CUDA and GPU driver workflows.

Qualifications

• BS/MS in Computer Science or Computer Engineering; 8+ years software engineering experience.
• Strong Python skills and experience with LangChain, LlamaIndex.
• Hands-on experience with RAG pipelines, tool-use / function-calling patterns, multi-step agentic services.
• Proven experience delivering agentic AI systems within a live production setting.
• Solid software engineering fundamentals: build, testing, observability, and scalable architecture.
• Strong analytical skills — comfortable reasoning about precision/recall tradeoffs, false positives, and evaluation methods for agent outputs.
• Experience building code agents — automated generation, review, or repair of real codebases.
• Background in GPU, driver, or systems software and familiarity with CUDA, kernel-mode software, or GPU driver development workflows.
• Experience with MCP servers, tool-calling agents, or multi-agent orchestration frameworks.
• Contributions to open-source AI tooling, agentic frameworks, or developer efficiency tools.
• Familiarity with CI/CD systems, crash analysis pipelines, or automated regression triage.

Responsibilities

• Compose, build, and productize agentic AI systems that operate on GPU software artifacts like source code, crash dumps, and CI/CD signals.
• Own the full lifecycle of agentic services from prototype through evaluation, deployment, and continuous improvement.
• Build robust LLM-powered pipelines for code generation, bug triage, regression detection, and intelligent test coverage analysis.
• Develop the agentic knowledge layer and MCP-based infrastructure enabling agents to interact with internal systems (Gerrit, NVBugs, CI/CD, Perforce, Slack).
• Design and assess agent quality—establish metrics, evaluations, and precision/recall tradeoffs at each funnel stage.
• Collaborate with GPU SW kernel engineers to identify high-impact automation opportunities and translate domain knowledge into agentic AI systems.
• Drive adoption across GPU SW teams by shipping fast, reliable agentic services that outperform manual approaches.

Skills

Python

LLM frameworks

Analytical skills

Production LLM systems

Education

BS/MS in Computer Science or Computer Engineering

Tools

LangChain

LlamaIndex

Gerrit

Perforce

NVBugs

CI/CD

Slack

Job description

NVIDIA Corporation in Santa Clara, CA invites applications for a senior role shaping agentic AI systems that operate directly on GPU software artifacts. You will build end-to-end pipelines for code generation, bug triage, and regression coverage, while driving automated, scalable AI solutions across GPU software teams.

The role demands 8+ years in software engineering with production LLM experience, strong Python, and familiarity with CUDA and GPU driver workflows.