As a Staff Software Engineer for ML Optimization and Hardware Acceleration at Rivian, you will be a key member of the Autonomy team, focusing on developing and optimizing advanced machine learning algorithms for self-driving features. This role emphasizes the integration of cutting-edge model architectures and high-performance hardware execution. You will work to bridge the gap between theoretical research and real-time deployment, ensuring the autonomy stack is both state-of-the-art and efficient. The position requires collaboration with various teams to optimize machine learning models for embedded platforms.

• MS degree with at least 3 years of experience in deep learning, heterogeneous computing, and ML accelerators, or a Ph.D. in Computer Science, Electrical Engineering, or a related field.
• Deep understanding of modern model architectures, including Transformers, LLMs, VLMs, and LDMs.
• Proven experience in model compression techniques such as knowledge distillation, pruning, and quantization.
• In-depth understanding of GPU architecture and optimization for diverse hardware specifications.
• Proficiency in Python and deep knowledge of PyTorch or TensorFlow.
• Hands-on experience with TensorRT, AIMET, and ONNX runtimes.
• Experience with low-level programming for inference logic, including CUDA kernels, C++, or BLAS subroutines.
• Experience with profiling tools like Torch Profiler and NVIDIA Nsight.

• Develop and deploy ultra-low latency Deep Learning and Machine Learning algorithms tailored for Rivian ADAS and Autonomy use cases.
• Research and implement hardware-aware optimization strategies to maximize throughput on embedded platforms.
• Utilize and automate deep-dive profiling tools to identify performance bottlenecks.
• Collaborate with low-level software and hardware architecture teams to optimize in-house ML models within strict compute and memory constraints.
• Apply a deep understanding of GPU architectures to optimize models across different hardware targets.
• Design and build automated pipelines for regular model profiling to enhance insight into execution bottlenecks.

• Employees at Rivian are often offered comprehensive health, dental, and vision insurance, a 401(k) with company match, ESPP and potential RSU grants, performance bonuses, and generous time off including paid parental and sick leave. Perks can include 24/7 mental-health coaching and therapy, Hinge Health for Anthem enrollees, tuition assistance and professional development, plus on-site food and a wide range of employee discounts on items like computers, mobile phones, home loans, and pet care.