Senior Platform AI Engineer — Agentic & LLM Systems

NVIDIA; Santa Clara (CA); On-site; USD 168,000 - 322,000; Full time

Benefits offered by this job

Equity

Health benefits

Paid time off

Job summary

NVIDIA in Santa Clara, CA seeks a deeply technical Senior Full-Stack Software Engineer to build the next generation AI platforms and products that push the boundaries of RAG and agentic AI, integrating with enterprise data sources and internal microservices. You will help shape architecture, scale, and delivery in a collaborative, fast-paced environment.

The role involves hands-on development, test automation, Linux and embedded systems work, and deploying in Kubernetes across cloud and hybrid

Qualifications

• 8+ years of experience building large-scale distributed systems and cloud-native applications (Python preferred).
• Strong experience designing and deploying LLM-powered systems, including RAG, tool use, and agent-based architectures.
• Deep understanding of agentic AI paradigms (planning, memory, tool invocation, multi-step reasoning).
• Experience with agent frameworks and orchestration tools (e.g., LangChain or similar).
• Proven ability to design systems with high reliability, scalability, and performance.
• Hands-on experience deploying applications in Kubernetes environments.
• Experience building systems in cloud and hybrid environments.
• Strong programming skills across multiple languages and modern software stacks.
• Proven track record leading complex technical initiatives and mentoring high-performing teams.

Responsibilities

• Hands-on experience with test automation, production testing, and automation frameworks
• Solid understanding of Linux, embedded systems, firmware, and hardware/software integration
• Deep knowledge of IT Service Management (ITSM) and ServiceNow (HR, Security, Finance modules preferred)
• Collaborate with cross-functional teams to deliver end-to-end intelligent experiences across applications
• Integrate agents with enterprise data sources, APIs, and internal microservices to enable real-world actions
• Architect and build agentic AI systems that leverage LLMs for reasoning, planning, and tool orchestration across enterprise workflows
• Develop scalable platforms for retrieval-augmented generation (RAG), long-term memory, and contextual reasoning
• Build reusable infrastructure for agent orchestration, tool integration, evaluation, and observability

Skills

Python

Distributed systems

Kubernetes

LangChain

LLM tooling

Cloud-native

Education

Bachelor's or Master's in CS/Engineering

Tools

LangChain

Docker

Job description

NVIDIA in Santa Clara, CA seeks a deeply technical Senior Full-Stack Software Engineer to build the next generation AI platforms and products that push the boundaries of RAG and agentic AI, integrating with enterprise data sources and internal microservices. You will help shape architecture, scale, and delivery in a collaborative, fast-paced environment.

The role involves hands-on development, test automation, Linux and embedded systems work, and deploying in Kubernetes across cloud and hybrid