Lead GPU Inference & ML Infrastructure Engineer

Avride Inc.; Austin (TX); On-site; USD 140,000 - 190,000; Full time

Job summary

Avride is seeking a software engineer with leadership experience to drive the ML infrastructure layer across the company. You will lead GPU inference optimization for onboard and high-throughput offboard scenarios, while guiding broader ML infrastructure across pipelines.

The role requires deep C++ experience, strong multi-threading skills, and collaboration with the applied ML team to align neural model architectures with performance goals.

Qualifications

• Experience with PyTorch and GPU architectures.
• Proven ability to diagnose and resolve performance issues in large systems.
• Strong track record building distributed infrastructure.

Responsibilities

• Own the GPU inference framework with a focus on performance.
• Take ownership of broader ML infrastructure across pipelines.
• Collaborate with the applied ML team on model architecture and deployment.

Skills

PyTorch

GPUs

Performance debugging

Infrastructure

C++

Multi-threading

Job description

Avride is seeking a software engineer with leadership experience to drive the ML infrastructure layer across the company. You will lead GPU inference optimization for onboard and high-throughput offboard scenarios, while guiding broader ML infrastructure across pipelines.

The role requires deep C++ experience, strong multi-threading skills, and collaboration with the applied ML team to align neural model architectures with performance goals.