Staff Machine Learning Compiler Engineer
Core
Lead the development of an ML Compiler to map Autonomy ML models to Rivian Autonomy Processor (RAP1) and enable efficient inference on Rivian hardware platforms.
Role type
Staff Machine Learning Compiler Engineer
Builds
Efficient building blocks for state-of-the-art machine learning models optimized for Rivian hardware.
Domain
Automotive / Autonomous Driving / Hardware-Software Co-design
Deliverable
production ML models
Required skills
C/C++, Python, Deep Learning frameworks, Compiler pipeline development, Hardware-aware optimizations, Quantization strategies, Model compression, Operator fusion, Embedded real-time constraints, Hardware profiling/debugging
Preferred skills
Hardware-software co-design for autonomous/robotics platforms, Quantization-aware training (QAT), Dynamic/static quantization flows, Model rearchitecture for hardware capabilities
Technologies
RAP1, Deep Learning frameworks, Low-level IRs
Responsibilities
Design and implement hardware-aware optimizations (quantization, compression, fusion) for RAP1; Collaborate with hardware teams to co-optimize model architecture and compute pipeline; Benchmark and analyze system performance across platforms; Partner with autonomy teams to align model optimization with hardware roadmap.
Seniority
Staff, hands-on IC with strategic alignment
