Engineering Intern - ML Compilers (Spring 2027 Co-op)
On-site
Core
Develop an ML Compiler to map Autonomy ML models to Rivian Autonomy Processor (RAP1) for hardware inference.
Role type
ML Compiler Engineer (Intern)
Builds
Software tools for deep learning network inference on Rivian Hardware Platforms
Domain
Automotive / Machine Learning / Compiler Engineering
Deliverable
production ML models
Required skills
C/C++, Python, Deep Learning frameworks, Compiler pipeline development, SOC platforms, Model compression, Quantization, Operator fusion
Preferred skills
Hardware-aware optimization, Low-level IRs
Responsibilities
Design and implement hardware-aware optimizations for RAP1; Collaborate with hardware teams to co-optimize model architecture; Benchmark and analyze system performance; Partner with autonomy teams to align optimization with hardware roadmap
