Senior System Software Engineer, Agentic Kernel Development

NVIDIA is hiring a Senior System Software Engineer, Agentic Kernel Development in Santa Clara, United States. It pays $184k-$288k a year and Level rates it ; you can apply on NVIDIA.

Level's read on this job

Builds AI ●●●● is how Level rates this software engineer role: the job is building AI systems.
Pay on this posting starts 10% higher than the typical software engineer posting on Level.
The posting mentions LangChain, LlamaIndex and RAG among its tools and skills.
Level classes it as a senior role.
NVIDIA has 1,800+ other open roles on Level.

AI in this role

langchainllamaindex

rag

Join NVIDIA's GPU SW Kernel organization, where we're groundbreaking the next generation of outstanding AI systems to transform GPU software development. Our team leads the effort in crafting agentic AI systems that improve the quality and efficiency of GPU software. This is an outstanding opportunity to grow innovative systems from promising projects to critically important infrastructure. Be part of a dynamic team that impacts GPU release quality and establishes new standards in AI-enhanced automation!

What you'll be doing:

Compose, build, and productize agentic AI systems that operate directly on GPU software artifacts — source code, crash dumps, changelists, test results, 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, 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!

What we need to see:

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
Proven experience delivering and refining agentic AI systems within a live production setting
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

Ways to stand out from the crowd:

Experience building code agents — automated generation, review, or repair of real codebases
Background in GPU, driver, or systems software (even as a user or collaborator) 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

Your base salary will be determined based on your location, experience, and other objective job-related factors. The expected base salary ranges for this position are:
184,000 USD – 287,500 USD for Level 4; and 224,000 USD – 356,500 USD for Level 5.

You will also be eligible for equity and benefits.

Applications for this job will be accepted at least until November 3, 2026.

This posting is for an existing vacancy.

NVIDIA uses AI tools in its recruiting processes.

NVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.

How we rate this

Senior System Software Engineer, Agentic Kernel Development at NVIDIA rates 93 out of 100 for how much of the daily work is AI. That makes it Builds AI (AI Level 4 of 4). The level is about AI in the job, not seniority.

Classification

Builds AI. The job is building AI systems.

●●●● Builds AI80 to 100
●●●○ Works on AI60 to 79
●●○○ Uses AI40 to 59
●○○○ Little AI0 to 39

Levels come from how often the tools, models and workflows of the role are named in the posting itself. Read the description and count the AI tools, models and workflows it names.

Key facts

Senior System Software Engineer, Agentic Kernel Development is an open job at NVIDIA.
Level rates this role AI Level 4 of 4: Builds AI.
The listed salary is $184k-$288k a year.
The role is based in US, CA, Santa Clara.
The job was posted on September 14, 2026.
Seniority: senior.
Applications are handled by NVIDIA. Apply on NVIDIA

Prepare for this job

Built from this posting and from similar jobs on Level.

Skills and AI tools this role asks for

RAGLangChainLlamaIndex

Also common in software engineer jobs at this level

C++Machine learning AWS AI agents Kubernetes Java

Pay

This job starts at: $184k
Typical software engineer job: $168k

This posting starts 10% above the typical software engineer job. See software engineer jobs

Questions you could be asked

How would you design a retrieval step so the model answers from real data instead of guessing?
Walk me through how you've used LangChain in your day-to-day work.
What are the limits of LlamaIndex that you've run into, and how did you work around them?
How would you decide a model or AI system is ready to ship?
Tell me about a time a model underperformed in production. How did you find out, and what did you change?

Adapt your resume

List these exact terms on your resume: RAG, LangChain, and LlamaIndex. An applicant tracking system matches the wording, not the idea.
Attach one line of real, concrete experience to at least one of them. A tool named with nothing behind it rarely survives a human read.
Lead with what you built, trained or shipped. This role is judged on the AI system itself, not the tools around it.

Want an expert to read your CV for this job?

Free. Send your CV and the role you want next. You get your review by email within 24 hours.

Get a free CV review Get your CV rewritten Check your resume with the ATS resume checker

Get new software engineer jobs (Builds AI ●●●●) by email

One email a week with the new software engineer jobs (Builds AI ●●●●), each rated for how much AI is in the work. No recruiter spam, unsubscribe in one click.

Free. One email a week. Unsubscribe in one click.