Lead Edge AI Engineer — Model Deployment & Optimization

Rivian; Camden Town; On-site; GBP 90,000 - 150,000; Full time

Job summary

Rivian, the electric vehicle pioneer, seeks a senior ML infrastructure engineer in London to lead edge AI workflows and deployment tooling. You will optimize models for low-power hardware, build compiler and model-ingestion pipelines, and collaborate with hardware, software, and product teams to scale a growing model zoo on RAP1 and future platforms.

You will mentor engineers, help shape the long-term edge AI stack, and drive memory, scheduling, and performance improvements across accelerators

Qualifications

• Deep experience in ML systems, deployment, or AI infrastructure.
• Background in edge/accelerated inference optimization.
• Experience building compiler/toolchain for ML workloads.

Responsibilities

• Lead development of ML enablement workflows for Rivian edge AI platforms.
• Build and improve front-end compiler and model-ingestion tooling for 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 ML models for deployment on hardware accelerators and NPUs.
• Improve performance across memory, scheduling, sparsity, and data-movement constraints with hardware/systems teams.
• Create methods to evaluate model fidelity and deployment quality across FP and int paths.
• Work with software, compiler, architecture, and product teams to identify high-value workloads.
• Provide technical leadership and mentoring for engineers in model deployment and hardware-aware ML.
• Shape long-term direction of Rivian’s edge AI stack for larger neural networks.

Skills

ML systems

Edge AI

Model optimization

Compiler tooling

Hardware accelerators

Cross-functional leadership

English communication

Education

Advanced degree in CS/ML

Tools

ONNX

TensorRT

Compiler toolchain

NPUs/GPUs

Job description

Rivian, the electric vehicle pioneer, seeks a senior ML infrastructure engineer in London to lead edge AI workflows and deployment tooling. You will optimize models for low-power hardware, build compiler and model-ingestion pipelines, and collaborate with hardware, software, and product teams to scale a growing model zoo on RAP1 and future platforms.

You will mentor engineers, help shape the long-term edge AI stack, and drive memory, scheduling, and performance improvements across accelerators