Lead GPU Performance Engineer — On-Site Irving

ZipStaff Inc.; Irving (TX); On-site; USD 140,000 - 170,000; Full time

Benefits offered by this job

Health Insurance

Dental Insurance

Vision Insurance

401(k) + 401(k) matching

Paid time off

Referral Program

Job summary

ZipStaff is hiring a Lead Software Engineer for a global heavy equipment manufacturer to accelerate robotics and physical AI by solving compute bottlenecks at scale. This on-site, 6-month contract role in Irving, TX (Mon–Fri, 8:00 AM–5:00 PM CT) offers the chance to push Omniverse, Isaac Sim and distributed multi-GPU clusters to performance limits.

As a technical lead, you will profile workloads with Nsight, refactor CUDA/C++ and Python code, and design agentic AI systems that optimize runtime

Qualifications

• Bachelor's or Master's degree in Computer Science, Computer Engineering or a related technical field.
• 7+ years of professional software engineering experience, including technical lead experience.
• Expert-level CUDA and modern C++ development, plus strong Python.
• Experience with NVIDIA Nsight tools to diagnose bottlenecks across CPU, GPU, memory, I/O and networking.
• Hands-on experience accelerating and scaling simulation workloads on Omniverse and Isaac Sim across multi-GPU and distributed systems.
• Deep knowledge of NVIDIA GPU architecture and memory hierarchy.
• Experience building agentic AI systems or LLM-driven developer tooling.
• Proven Linux experience and containerized GPU workloads with Docker, Kubernetes and Slurm on CoreWeave, AWS or Azure.
• Strong understanding of parallel computing, memory hierarchies and multi-GPU/distributed scaling (NCCL, MPI).
• Experience with CI/CD, automated regression testing and performance benchmarking.
• On-site work in Irving, TX.

Responsibilities

• Profile and optimize workloads, diagnosing bottlenecks across CPU, GPU, memory, I/O, storage and networking using NVIDIA Nsight tools.
• Refactor and tune core simulation code in CUDA, C++ and Python to maximize hardware utilization, throughput and execution speed.
• Design and deploy agentic AI systems that automatically analyze and optimize runtime code performance.
• Accelerate and scale simulation workloads on NVIDIA Omniverse and Isaac Sim across multi-GPU and distributed systems.
• Manage and optimize containerized GPU jobs using Docker, Kubernetes and Slurm across cloud environments.
• Implement automated regression testing, observability and performance benchmarking for continuous performance tracking.
• Partner with robotics, perception and AI teams to drive GPU performance best practices and evaluate future hardware and software infrastructure.

Skills

CUDA

C++

Python

NVIDIA Nsight

Linux

Multi-GPU

CI/CD

MPI/NCCL

Docker/Kubernetes

Slurm

Education

Bachelor's in CS/CE

Master's in CS/CE

Tools

NVIDIA Nsight tools

Omniverse

Isaac Sim

Docker

Kubernetes

Slurm

Prometheus

Grafana

Job description

ZipStaff is hiring a Lead Software Engineer for a global heavy equipment manufacturer to accelerate robotics and physical AI by solving compute bottlenecks at scale. This on-site, 6-month contract role in Irving, TX (Mon–Fri, 8:00 AM–5:00 PM CT) offers the chance to push Omniverse, Isaac Sim and distributed multi-GPU clusters to performance limits.

As a technical lead, you will profile workloads with Nsight, refactor CUDA/C++ and Python code, and design agentic AI systems that optimize runtime