AI Infra Onboard Performance Intern
Core
Design and optimize software for deploying large-scale AI models in production vehicles, focusing on inference performance, latency reduction, and power efficiency on embedded automotive platforms.
Role type
AI Infrastructure Performance Intern
Builds
Production-ready optimizations for large-scale AI models in vehicles
Domain
Automotive AI / Embedded Systems / High-Performance Computing
Deliverable
production ML models
Required skills
C++, Python, Computer Architecture, High-Performance Computing, Application Performance Analysis, Profiling Tools
Preferred skills
CUDA Kernel Optimization, Performance Tooling (eBPF, perf), Embedded/Automotive Compute Platforms, Autonomous Driving/Robotics Experience
Technologies
C++, Python, CUDA, eBPF, perf, NVIDIA Orin, NVIDIA Drive
Responsibilities
Profile and improve inference performance across compute, memory, and I/O systems; Reduce latency and improve power efficiency on embedded automotive platforms; Deliver production-ready optimizations that scale reliably across the vehicle fleet
Seniority
Intern