Deep Learning Software Engineer, TensorRT Performance - New College Grad 2027
$124k - $242k • Remote • US, CA, Santa Clara
Posted 7d ago
Job Location
US, CA, Santa Clara
Tech Stack
Remote Work Policy
Fully remote
Categories
Machine Learning Engineer
About the job
NVIDIA is seeking passionate Deep Learning Software Engineers to analyze and improve the performance of NVIDIA's inference ecosystem. Join a rapidly growing team focused on Deep Learning Inference, enabling companies worldwide to power breakthroughs in Generative AI, Recommenders, and Vision. This role involves developing GPU-accelerated deep learning inference software like TensorRT, creating DL benchmarking software, and building performant solutions for model deployment and serving. You will collaborate with the deep learning community to integrate TensorRT into open-source frameworks and optimize state-of-the-art models across various NVIDIA accelerators, from data center GPUs to edge SoCs. The work includes implementing graph compiler algorithms, frontend operators, and code generators within NVIDIA's inference ecosystem, alongside collaborating with diverse teams on workflow improvements, performance modeling, analysis, kernel development, and inference software development.
Responsibilities
- Establish performance benchmarking methodologies and analysis workflows to identify issues and opportunities within NVIDIA's inference ecosystem (e.g., TensorRT, TensorRT-EdgeLLM, Torch-TensorRT).
- Contribute features and code to NVIDIA and open-source inference frameworks like TensorRT, TensorRT-EdgeLLM, and Torch-TensorRT.
- Develop new, optimized model pipelines for NVIDIA's inference ecosystem, focusing on areas like quantization, scheduling, memory management, and distributed inference for Generative AI performance.
- Collaborate with internal and external teams across various domains (generative AI, automotive, robotics, image understanding, speech understanding) to develop innovative inference solutions.
- Scale the performance of deep learning models across different architectures and types of NVIDIA accelerators.
Requirements
- Bachelor's, Master's, PhD, or equivalent experience in Computer Science, Computer Engineering, EECS, or AI.
- 2 years of relevant software development experience.
- Strong C++, Python programming, and software engineering skills.
- Experience with deep learning frameworks (e.g., PyTorch, JAX, TensorFlow, ONNX) and inference libraries (e.g., TensorRT, TensorRT-LLM, vLLM, SGLang, FlashInfer).
- Experience with performance analysis and optimization.
Benefits
- Equity
- Benefits
- Base salary range for Level 2: 124,000 USD - 195,500 USD
- Base salary range for Level 3: 152,000 USD - 241,500 USD