Avride is seeking a Lead AI Infrastructure Engineer to shape the company’s ML infrastructure. You will lead the GPU inference framework with a focus on performance for onboard real-time applications and for offboard high-throughput, deterministic execution. Initially you will own the GPU inference framework and, over time, assume ownership of broader ML infrastructure across ML pipelines. You will collaborate closely with the Applied ML team responsible for defining the neural model architecture. Requirements include 5+ years of C++ experience, strong multi-threaded programming skills, PyTorch experience, a solid understanding of GPU operation, and a proven ability to diagnose and resolve performance issues, plus a track record of building distributed infrastructure. Authorization to work in the United States is required; relocation sponsorship and remote work options are not available. Avride is an equal opportunity employer and provides accommodations as required by law.

Avride is seeking a Lead AI Infrastructure Engineer to shape the company’s ML infrastructure. You will lead the GPU inference framework with a focus on performance for onboard real-time applications and for offboard high-throughput, deterministic execution. Initially you will own the GPU inference framework and, over time, assume ownership of broader ML infrastructure across ML pipelines. You will collaborate closely with the Applied ML team responsible for defining the neural model architecture. Requirements include 5+ years of C++ experience, strong multi-threaded programming skills, PyTorch experience, a solid understanding of GPU operation, and a proven ability to diagnose and resolve performance issues, plus a track record of building distributed infrastructure. Authorization to work in the United States is required; relocation sponsorship and remote work options are not available. Avride is an equal opportunity employer and provides accommodations as required by law.