Deep Learning Software Engineer

About the Role

NVIDIA is seeking Deep Learning Software Engineers passionate about analyzing and improving the performance of NVIDIA’s inference ecosystem. Join the team that builds the software to enable the performance optimization, deployment, and serving of deep learning inference solutions, specializing in GPU-accelerated deep learning inference software like TensorRT, DL benchmarking software, and performant solutions.

Key Responsibilities

• Establish groundbreaking performance benchmarking methodologies and analysis workflows to identify performance issues and opportunities for NVIDIA’s inference ecosystem (e.g., TensorRT, TensorRT-EdgeLLM, Torch-TensorRT).
• Contribute features and code to NVIDIA/OSS inference frameworks including but not limited to TensorRT, TensorRT-EdgeLLM, and Torch-TensorRT.
• Develop new model pipelines for NVIDIA’s inference ecosystem with optimized performance, including areas like quantization, scheduling, memory management, and distributed inference, to set the gold standard for Gen AI performance.
• Work with cross-collaborative teams inside and outside of NVIDIA across generative AI, automotive, robotics, image understanding, and speech understanding to set directions and develop innovative inference solutions.
• Scale performance of deep learning models across different architectures and types of NVIDIA accelerators.
• Implement graph compiler algorithms, frontend operators, and code generators across NVIDIA’s inference ecosystem.
• Identify performance opportunities and optimize SoTA models across the spectrum of NVIDIA accelerators, from datacenter GPUs to edge SoCs.
• Work and collaborate with a diverse set of teams involving workflow improvements, performance modeling, performance analysis, kernel development, and inference software development.

Requirements & Tech Stack

• Strong C++, Python programming and software engineering skills.
• Experience with DL frameworks (e.g., PyTorch, JAX, TensorFlow, ONNX) and inference libraries (e.g., TensorRT, TensorRT-LLM, vLLM, SGLang, FlashInfer).
• Experience with performance analysis and performance optimization.

Qualifications

• Bachelor's, Master's, PhD, or equivalent experience in relevant fields (Computer Science, Computer Engineering, EECS, AI).
• 2 years of relevant software development experience.

Ways To Stand Out

• Strong foundation and architectural knowledge of GPUs.
• Deep understanding of modern deep learning models and workloads (e.g., Transformers, Recommenders, ASR, TTS, Visual Understanding).
• Proficiency in one of the deep learning programming domain specific languages (e.g., CUDA, TileIR, CuTeDSL, cutlass, Triton).
• Prior contributions to major LLM inference frameworks (e.g., vLLM) or prior experience with graph compilers in deep learning inference (e.g., TorchDynamo/TorchInductor).
• Prior experience optimizing performance for low-latency, resource-constrained systems or embedded AI pipelines (e.g., Jetson systems or other edge AI accelerators).