Avride
Lead AI Infrastructure Engineer
Austin, Texas · Full-time · Posted Sep 29, 2026
- Experience
- 5+ years of experience with C++.
- Visa sponsorship
- Candidates must be authorized to work in the U.S. The employer does not offer sponsorship.
About the job
Lead development and performance optimization of GPU inference and broader ML infrastructure for Avride’s self-driving systems, supporting onboard autonomy and large-scale simulation.
What you'll do
- Take ownership of the GPU inference framework, with an initial focus on performance.
- Assume responsibility for broader ML infrastructure across ML pipelines.
- Collaborate with the applied ML team on neural model architecture.
What they ask for
- Experience with PyTorch.
- Understanding of how GPUs work.
- Experience diagnosing and resolving performance issues, and a strong record of building infrastructure including distributed systems.
- 5+ years of experience with C++; programming experience in multi-threaded environments involving multiple processes, threads, timers, and interrupts.
Tools
PyTorch, C++, GPU
AI focus
Optimize GPU inference for neural networks, targeting near-real-time onboard latency and high-throughput, deterministic execution in simulation; build and maintain ML infrastructure.
Model-written summary · the original posting is authoritative