Platform Engineer, ML Ops

Wayve is seeking a Platform Engineer, ML Ops to join their Inference Optimization team. This role is based in Sunnyvale and offers a hybrid working environment.

About Wayve:

Wayve is a leading developer of Embodied AI technology, creating AI software and foundation models for autonomous vehicles. They value diversity and foster an inclusive work environment.

The Role:

This role involves building and owning the automatic deployment pipeline for compiling and validating AI driving models on multiple target embedded platforms. The Platform Engineer will work at the intersection of machine learning and embedded systems, enabling the deployment of driving models onto autonomous vehicles.

Key Responsibilities:

• Build and own the CI/CD model deployment pipeline for compiling and optimizing AI models.
• Collaborate with model developers, compiler engineers, and GPU kernel engineers to automate the compilation process.
• Plan roadmap milestones and execute against them as a hands-on tech lead.
• Identify key roles and skillsets to grow the team.
• Develop new skills in model optimization and deployment.

Requirements:

• Over 8 years of experience in Site Reliability Engineering or a similar role.
• Experience as a technical leader or senior engineer on projects involving deployment pipelines, containerization (Docker, Kubernetes), and CI/CD.
• Proficiency in Python and C++.
• Excellent interpersonal and communication skills.
• Exceptional problem-solving skills and a detail-oriented mindset.

The role offers:

• Opportunities to develop new skills, especially in model optimization and deployment