Lead Software Engineer at Gazelle Systems in Irving, TX

Caterpillar needs an onsite Lead Software Engineer in Irving, TX to find and remove compute bottlenecks in robotics and physical AI simulation. The work centers on tuning CUDA, C++ and Python code, scaling NVIDIA Omniverse and Isaac Sim workloads across multi-GPU and distributed clusters, and building agentic AI systems that automatically analyze and optimize code performance.

Responsibilities

• Profile & Optimize Workloads: Diagnose and eliminate performance bottlenecks across CPU, GPU, memory, I/O, storage, and networking layers using NVIDIA Nsight tools Tune CUDA, C++, and Python
• Refactor and optimize core simulation code 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 running 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 (CoreWeave, AWS, Azure).
• Implement automated regression testing, observability, and performance benchmarking for continuous tracking.
• Partner with robotics, perception, and AI teams to drive GPU performance best practices and evaluate future hardware/software infrastructure.

Qualifications

• Strong analytical, troubleshooting, and problem-solving skills.
• Hands-on experience designing and deploying AI agents.
• Proven experience with CUDA; C++; Python; NVIDIA Omniverse and Isaac Sim
• Ability to work independently under pressure during high-severity incidents while maintaining clear communication with stakeholders

This is a W2 contract for 6 months with an option for extention

Pay: $135,000.00 - $144,000.00 per year

Benefits:

• Health insurance

Work Location: In person