Manager, RL Algorithms & Decoder

The Onboard Behavior Model Architecture team is responsible for developing deep learning models that leverage data and compute at large scale to train driving models. We learn and predict behaviors from large scale expert data and large scale reinforcement learning to produce a ML driver that is safe, comfortable, and completes the mission. In this role, you will collaborate closely with the Onboard Perception, Cost Planner, Simulation, Validation, Data Science, Systems Engineering, QA, and ML Infra teams.

In this role, you will:

• Lead a Team: Manage, mentor, and grow a team of individual contributors, fostering a culture of innovation and continuous improvement.
• Develop Strategy: Develop and organize our overall strategy for Onboard Behavior ML Models for generating driving plans for our autonomous vehicle. You will interface with multiple partner teams to identify opportunities for model improvements within their problem area. You’ll be setting the short and long term technical direction for the team and collaborate on broader company-wide directions.
• Provide technical guidance and leadership in the design and development of training models at large scale and work with partner teams on ensuring their efficient inference.
• Monitor Performance: Establish and monitor key performance indicators (KPIs) to measure the effectiveness of work packages and drive continuous improvement.
• Manage Resources: Manage the allocation of resources within the team, ensuring that projects are staffed appropriately and that team members have the necessary tools and support to succeed.

Qualifications

• Expertise with Reinforcement Learning and Machine Learning for at least one of these areas: Planning, LLMs, VLAs/VLMs, recommendation systems.
• Extensive experience with programming and algorithm design, strong mathematics skills.
• MS or PhD degree in computer science or related field.
• 5+ years of experience with production Machine Learning pipelines, with at least 3 years in a leadership or management role.

Bonus Qualifications

• Conference or Journal publications in Machine Learning or Robotics related venues.
• Prior experience working with autonomous vehicles or robotics, diffusion models, large scale training.

Seen 21 days ago · Zoox postings close after a median of 10 days.

Original posting on Zoox's site ↗

Posting text belongs to the employer. Removal requests: contact us.