Inference Optimization Manager

The Role

As the Manager of the Inference Optimization team at Wayve, you will steer our pioneering efforts to refine and productize AI models for autonomous driving features in consumer vehicles. Occupying a critical junction between machine learning and embedded systems, you will lead the strategic direction and provide comprehensive oversight to a team committed to enhancing the efficiency and performance of our autonomous vehicle (AV) AI models to ensure their maximal performance on automotive embedded compute platforms. From the initial stages of development to the final phases of deployment, your expertise will ensure the seamless integration of AI into automotive technologies, requiring a profound grasp of AI model optimization, edge computing, and embedded systems within the automotive sector.

Key responsibilities:

• Team Leadership and Strategy: Spearhead a multidisciplinary team of Machine Learning Engineers, Embedded Kernel Engineers, and Software Engineers, setting clear objectives and milestones for optimization projects. Drive the vision and strategy for deploying cutting-edge AI models in AV systems, ensuring alignment with Wayve’s overarching goals
• Optimization Framework Development: Oversee the creation and refinement of optimization frameworks that enhance the computational efficiency of AI models while maintaining or improving model accuracy and inference speed
• Cross-functional Collaboration: Facilitate seamless cooperation between the machine learning, software engineering, and embedded systems teams. Ensure that model development and optimization efforts are synchronized with hardware capabilities and deployment requirements
• Performance Benchmarking: Establish rigorous benchmarking standards for model performance, including computational efficiency, inference speed, and power consumption, guiding the team in achieving and surpassing these benchmarks
• Innovation and Research: Promote a culture of continuous improvement and innovation, encouraging the team to explore novel optimization techniques, including quantization, model pruning, and advanced compiler technologies
• Resource Allocation: Efficiently manage resources, including personnel and computing infrastructure, to meet project deadlines and performance targets
• Talent Development: Recruit, mentor, develop, and retain your team, fostering a growth mindset and technical excellence. Identify skill gaps and champion training and recruitment efforts to build a world-class inference optimization team

Essential :

• Proven Leadership: At least 5 years of experience in a leadership role within the fields of machine learning, embedded systems, or a related area, with a track record of managing high-performing technical teams
• Expertise in AI and Embedded Systems: A solid understanding of AI model optimization techniques, edge computing, and embedded system design, ideally within the automotive or similar high-stakes industries
• Technical Proficiency: Hands-on experience with AI model development and optimization tools such as PyTorch, CUDA, and TensorRT. Familiarity with programming languages including Python and C++
• Strategic Thinking: Strong ability to develop and execute strategic plans for technology development, aligning with both short-term and long-term objectives
• Collaborative Skills: Excellent interpersonal and communication skills, with a proven ability to foster collaboration across diverse technical teams.
• Educational Background: A Master’s degree in Computer Science, Electrical Engineering, or a related field is required. A Ph.D. is highly preferred, along with a robust record of relevant research.

This is a full-time role based in our office in Sunnyvale, CA.  At Wayve we want the best of all worlds so we operate a hybrid working policy that combines time together in our offices and workshops to fuel innovation, culture, relationships and learning, and time spent working from home.   We operate core working hours so you can determine the schedule that works best for you and your team.  

#LI-AB1