GPU Performance & Simulation Infrastructure Lead

GPU Performance & Simulation Infrastructure Lead

Accelerate the future of robotics and physical AI by solving high-impact compute bottlenecks at scale. In this high-visibility technical lead role, you will pioneer automated, agentic code optimization and push NVIDIA Omniverse, Isaac Sim, and distributed multi-GPU clusters to their absolute performance limits.

Core Stack

• Languages: CUDA, C++, Python
• AI & Simulation: Agentic AI, NVIDIA Omniverse, Isaac Sim
• Tooling & Infrastructure: NVIDIA Nsight (Systems, Compute, Graphics), Docker, Kubernetes, Slurm
• Cloud Environments: CoreWeave, AWS, Azure

Key Responsibilities & Duties

• Workload Profiling & Diagnostics: Diagnose and eliminate performance bottlenecks across CPU, GPU, memory, I/O, storage, and networking layers using NVIDIA Nsight tools.
• Code Refactoring & Tuning: Refactor and tune CUDA, C++, and Python simulation code to maximize hardware utilization, throughput, and execution speed.
• Agentic Systems: Design and deploy agentic AI systems that autonomously analyze and optimize runtime code performance.
• Simulation Scaling: Accelerate and scale simulation workloads on NVIDIA Omniverse and Isaac Sim across multi-GPU and distributed systems.
• Cluster & Cloud Orchestration: Manage and optimize containerized GPU jobs using Docker, Kubernetes, and Slurm across CoreWeave, AWS, and Azure.
• Observability & Benchmarking: Implement automated regression testing, observability, and performance benchmarking for continuous tracking.
• Cross-Functional Leadership: Partner with robotics, perception, and AI teams to drive GPU performance best practices and evaluate next-generation hardware/software infrastructure.

Required Qualifications

• Education: Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related technical field.
• Core Languages: Strong programming proficiency in C++ and Python.
• GPU Architecture & CUDA: Deep expertise in CUDA programming, GPU performance optimization, and NVIDIA GPU memory hierarchy/architecture.
• Agentic AI: Strong background building agents for automated code analysis and runtime optimization.
• Simulation Platforms: Hands-on experience with NVIDIA Omniverse, Isaac Sim, or equivalent simulation engines.
• Profiling Tooling: Practical experience using NVIDIA Nsight tools (Nsight Systems, Nsight Compute, Nsight Graphics).
• Distributed Computing: Solid knowledge of multi-GPU systems, parallel processing, and distributed computing environments.
• Containers & Orchestration: Proven experience with Linux, containerized workloads (Docker), and cluster orchestrators (Kubernetes, Slurm).
• Cloud Infrastructure: Hands-on experience deploying and optimizing workloads on GPU cloud platforms (CoreWeave, AWS, or Azure).
• Benchmarking & Efficiency: Proven track record in benchmarking, debugging, and tuning compute-intensive workloads for maximum throughput and cost efficiency.

Preferred Skills & Experience

• Optimizing RTX and real-time rendering workloads.
• Background in robotics, autonomous systems, digital twins, or simulation platforms.
• Knowledge of High-Performance Computing (HPC) environments and large-scale GPU clusters.
• Experience with CI/CD pipelines and automated performance benchmarking frameworks.
• Familiarity with machine learning infrastructure, AI training, and synthetic data generation.
• Scaling simulation platforms used for autonomy, perception, or physical AI development.