Senior Software Engineer, Machine Learning Inference

Job Description

Design, develop, and optimize NVIDIA TensorRT and TensorRT-LLM to enhance inference applications for datacenters, workstations, and PCs. Collaborate with GPU architects and deep learning experts to influence hardware and software design for AI accelerators.

Requirements: Requires a degree in Computer Science or a related field with over 4 years of software development experience on large codebases. Proficiency in C++ is mandatory, along with experience in deep learning frameworks, compilers, or system software.

Key Skills: C++, Python, CUDA, Machine Learning Inference, TensorRT, TensorRT-LLM, Deep Learning Frameworks, Compilers, System Software, GPU Programming, LLM Inference, PyTorch, JAX, Performance Analysis, Rust, OpenCL

Benefits: Equity