Hardware machine learning/AI engineer on edge platforms

Rivian is on a mission to keep the world adventurous forever. This goes for the emissions-free Electric Adventure Vehicles we build, and the curious, courageous souls we seek to attract. Rivian is looking for a Sr Staff Machine Learning/AI Engineer to help expand the capabilities of our ML application and compiler ecosystem for edge AI platforms.

• Lead development of machine learning enablement workflows for Rivian edge AI platforms.
• Build and improve front-end compiler and model-ingestion tooling needed to support a broad model zoo on RAP1 and future platforms.
• Develop and scale robust quantization-aware training and model optimization infrastructure.
• Port, optimize, validate, and benchmark machine learning models for deployment on hardware accelerators and NPU-class architectures.
• Improve performance across memory, scheduling, sparsity, and data-movement constraints in close collaboration with hardware and systems teams.
• Create methods to evaluate model fidelity and deployment quality across floating-point and quantized paths, including accuracy, error, and performance tradeoffs.
• Work across software, compiler, architecture, and product teams to identify the highest-value workloads and accelerate customer-relevant enablement.
• Provide technical leadership and mentoring for engineers working on model deployment, compiler infrastructure, and hardware-aware ML.
• Help shape the long-term direction of Rivian’s edge AI stack, including support for increasingly large and complex neural network models.

• Deep experience in machine learning systems, model deployment, or AI infrastructure.
• Strong background in model optimization for edge or accelerated inference, including quantization and performance tuning.
• Experience building or extending compiler, toolchain, or graph-transformation infrastructure for ML workloads.
• Strong understanding of hardware/software co-design for inference acceleration.
• Experience working with low-power edge platforms, NPUs, custom accelerators, GPUs, or closely related architectures.
• Ability to reason about memory allocation, execution scheduling, bandwidth constraints, and overall system performance.
• Experience translating research concepts into practical tooling and production workflows.
• Strong cross-functional communication skills and the ability to lead through technical influence.
• Будет плюсом: Experience with quantization-aware training, post-training quantization, compression, pruning, and sparsity optimization; Experience bringing vision or multimodal models from development through full deployment; Familiarity with ONNX and model graph transformation pipelines; Experience validating numerical behavior across float and integer execution paths; Experience supporting external customers, partner enablement, or productization of AI platforms; Background working with both model-level and hardware-level optimization problems; Startup or founder-level experience building end-to-end AI platform capabilities

• Условий в вакансии нет