Senior Systems Architect - Agentic AI Runtime & Inference

NVIDIA; Austin (TX); On-site; USD 224,000 - 431,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA in Austin is seeking a Senior Software Architect to lead the design of scalable agentic AI systems, spanning runtimes, inference, evaluation, and orchestration. You will prototype ideas, write production code, and provide technical leadership across research, engineering, product and infrastructure teams.

You should have 12+ years in CS or related fields, a strong AI foundation, deep distributed-systems expertise, and hands-on Python, C++, Go or Rust skills.

Qualifications

• BS, MS, or equivalent experience in Computer Science/Engineering or AI with 12+ years in the field.
• Strong foundation in modern AI, including LLMs, multimodal models, inference, and evaluation.
• Deep expertise in software architecture and large-scale distributed systems design.
• Hands-on programming in Python, C++, Go or Rust with production-grade software
• Experience building large-scale distributed pipelines, HPC, cloud, and GPU infrastructures.
• Ability to reason across AI model behavior to runtime and infrastructure.

Responsibilities

• Architect and build scalable, reliable systems for agentic AI across runtimes, harnesses, inference, evaluation, and orchestration.
• Address large-scale distributed execution, data/ETL, HPC, cloud, Kubernetes, and GPU compute challenges.
• Improve reliability, scalability, performance, resource use, and developer experience.
• Prototype ideas, write production-grade code, and provide technical leadership across teams.

Skills

Python

C++

Go

Rust

Software architecture

Distributed systems

Large-scale systems design

AI breadth (LLMs, multimodal)

Education

BS

MS

Job description

NVIDIA in Austin is seeking a Senior Software Architect to lead the design of scalable agentic AI systems, spanning runtimes, inference, evaluation, and orchestration. You will prototype ideas, write production code, and provide technical leadership across research, engineering, product and infrastructure teams.

You should have 12+ years in CS or related fields, a strong AI foundation, deep distributed-systems expertise, and hands-on Python, C++, Go or Rust skills.