Senior AI Performance Engineer (CUDA / GPU / NVIDIA Stack)

Job Title: Senior AI Performance Engineer (CUDA / GPU / NVIDIA Stack)
Duration: Min 12+ Months
Location: 100% Remote
Job Description:
This is a hands-on engineering role, requiring deep expertise in CUDA, GPU architecture, and performance profiling.
Key Responsibilities
• Profile and optimize AI/ML workloads across multi-GPU and multi-node systems
• Identify bottlenecks across compute, memory, networking, and orchestration layers
• Optimize CUDA kernels (memory coalescing, shared memory usage, occupancy tuning)
• Improve inference performance using TensorRT, Triton, DeepStream, NeMo
• Analyze and improve latency, throughput, GPU utilization, and memory efficiency
• Work on distributed AI systems using Apache Ray, NCCL, Kubernetes GPU scheduling
• Build benchmarking frameworks and performance monitoring systems
• Collaborate with AI, DevOps, and Infrastructure teams for system-wide optimization
Required Skills
• Strong hands-on CUDA programming and GPU performance optimization
• Deep understanding of GPU architecture and memory hierarchy
• Experience with Nsight, CUDA profiling tools, performance benchmarking
• Hands-on experience with NVIDIA ecosystem (Triton, TensorRT, NeMo, DeepStream)
• Experience with distributed AI systems (multi-GPU, multi-node, NCCL, Ray)
• Experience working with AI models such as YOLO, GPT, LLaMA, Transformers
• Strong understanding of AI system performance metrics (latency, throughput, utilization)
Preferred
• Experience working at NVIDIA or similar GPU/AI infrastructure companies
• Experience with real-time video / Vision AI systems
• Experience with large-scale production AI deployments
Interview Process (Mandatory)
• Candidates will receive a technical handout 1 day before interview
• 90-minute deep-dive demo discussion (NOT theoretical)
• Candidate must explain:
o Bottleneck identification approach
o GPU optimization strategies
o System-level performance improvements