Lead AI Infrastructure Engineer
Based in United States
Core
Building the GPU inference framework and ML infrastructure layer for Avride's self-driving stack to ensure stable latencies for onboard applications and high throughput for simulation.
Role type
Lead AI Infrastructure Engineer
Builds
GPU inference framework, execution graph systems, and ML infrastructure pipelines
Domain
Autonomous driving / Self-driving technology
Deliverable
production ML models
Required skills
C++, PyTorch, GPU architecture, distributed systems, multi-threaded programming, performance optimization
Responsibilities
Design and optimize GPU inference framework for near real-time guarantees, own broader ML infrastructure across pipelines, collaborate with applied ML teams on neural model architecture
Seniority
Senior, hands-on IC with leadership