Lead AI Infrastructure Engineer
On-siteAustin, Texas, United States
Job Summary
Optimize GPU inference frameworks for onboard near real-time latency and offboard high throughput, ensuring deterministic execution across both environments. Diagnose and resolve performance issues within distributed systems while building broader ML infrastructure across pipelines. Collaborate closely with applied ML teams to define neural model architectures and influence the company's ML infrastructure layer. Requires 5+ years of C++ experience, deep understanding of GPU mechanics, and proficiency in multi-threaded environments using PyTorch. This role is critical to Avride's self-driving stack, powering the base infrastructure layer for autonomy components and execution graphs.
Required Qualifications
- Experience with PyTorch
- Understanding of how GPUs work
- Experience in diagnosing and resolving performance issues
- Strong record of building infrastructure including distributed systems
- 5+ years of experience with C++
- Programming experience in multi-threaded environments - multiple processes, threads, timers, and interrupts
- Candidates are required to be authorized to work in the U.S.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.