3 days ago
Base Salary
$124k - $242k/yr
Responsibilities
- Establish benchmarking methodologies and performance-analysis workflows for NVIDIA’s deep learning inference ecosystem.
- Identify performance issues and optimize state-of-the-art models across datacenter GPUs and edge SoCs.
- Contribute features and code to TensorRT, TensorRT-EdgeLLM, Torch-TensorRT, and related open-source inference frameworks.
- Develop optimized inference pipelines involving quantization, scheduling, memory management, and distributed inference.
- Collaborate across generative AI, automotive, robotics, image understanding, and speech understanding teams.
- Scale deep learning model performance across different NVIDIA accelerator architectures.
Requirements
- Bachelor’s, master’s, PhD, or equivalent experience in computer science, computer engineering, EECS, AI, or a relevant field.
- At least two years of relevant software development experience.
- Strong C++, Python, and software engineering skills.
- Experience with deep learning frameworks such as PyTorch, JAX, TensorFlow, and ONNX.
- Experience with inference libraries such as TensorRT, TensorRT-LLM, vLLM, SGLang, and FlashInfer.
- Experience with performance analysis and performance optimization.
- Preferred: strong GPU architectural knowledge and understanding of modern deep learning models and workloads.
- Preferred: proficiency in CUDA, TileIR, CuTeDSL, CUTLASS, or Triton.
- Preferred: contributions to LLM inference frameworks or experience with deep learning graph compilers such as TorchDynamo or TorchInductor.
- Preferred: experience optimizing low-latency, resource-constrained systems or embedded AI pipelines such as Jetson systems.
Benefits
- Eligible for equity and benefits.
- Base salary is determined by location, experience, and comparable employee pay.
- Applications will be accepted at least until October 16, 2026.
- NVIDIA is an equal opportunity employer committed to an inclusive work environment.
Categories
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.