Application Guide

How to Apply for Machine Learning Engineer - Perception

at Zoox

🏢 About Zoox

Zoox is pioneering fully autonomous, purpose-built electric vehicles designed specifically for dense urban environments, not retrofitting existing cars. Their unique approach combines vehicle design, AI, and robotics into an integrated system, offering the rare opportunity to work on end-to-end autonomous driving from sensor fusion to vehicle deployment. Working here means contributing to a vision of reducing urban congestion and emissions through innovative transportation solutions.

About This Role

This Machine Learning Engineer - Perception role focuses on developing multi-sensor fusion deep learning models to detect and understand obstacles in complex urban environments, then deploying optimized models to Zoox's robot fleet. You'll be solving critical perception challenges around rare obstacles and extreme weather conditions that directly impact vehicle safety and autonomy. Your work bridges the gap between model development and real-world deployment in autonomous vehicles.

💡 A Day in the Life

A typical day involves analyzing perception model performance on challenging urban scenarios, collaborating with the data team to curate datasets for specific obstacle types, and optimizing model architectures for latency on vehicle hardware. You'll work closely with the Prediction/Planner team to understand how perception outputs affect downstream decisions and participate in reviews of difficult edge cases from fleet data.

🚀 Application Tools

Generate Cover Letter

AI-powered, tailored for Zoox

Interview Prep

Practice questions for this role

🎯 Who Zoox Is Looking For

  • Has 5+ years of industry experience with MS/PhD in ML/CS and deep expertise in multi-sensor fusion algorithms for object detection, segmentation, or tracking
  • Demonstrates practical experience with Transformer architectures and can discuss specific implementations or optimizations they've worked on
  • Has published in top-tier computer vision conferences (CVPR, ICCV, ECCV) or has equivalent industry contributions to perception systems
  • Can articulate experience with both real and synthetic dataset curation specifically for autonomous vehicle perception challenges

📝 Tips for Applying to Zoox

1

Highlight specific multi-sensor fusion projects in your resume - mention which sensors (LiDAR, cameras, radar) you fused and the algorithms used

2

Include metrics from your previous work: model accuracy, latency improvements, or deployment success rates on edge devices or vehicles

3

Mention any experience with rare obstacle detection or extreme weather conditions in autonomous driving contexts

4

If you have publications, link to them and briefly explain how they relate to Zoox's perception challenges

5

Demonstrate your C++ knowledge alongside Python - mention specific projects where you used C++ for deployment or optimization

✉️ What to Emphasize in Your Cover Letter

['Explain your specific experience with multi-sensor fusion for autonomous vehicles and how it addresses perception gaps', 'Describe a project where you optimized model latency for real-time deployment, especially on edge or vehicle hardware', 'Discuss your approach to working with both real and synthetic datasets to improve model robustness', "Connect your background to Zoox's specific challenges with difficult obstacles and complex urban driving scenarios"]

Generate Cover Letter →

🔍 Research Before Applying

To stand out, make sure you've researched:

  • → Study Zoox's vehicle design and sensor suite to understand their specific multi-sensor fusion challenges
  • → Research their approach to synthetic data generation and how they've discussed it in blogs or presentations
  • → Look into their specific deployment environments - which cities they're testing in and what unique obstacles exist there
  • → Review their technical blog posts about perception challenges and recent publications from their team

💬 Prepare for These Interview Topics

Based on this role, you may be asked about:

1 Technical deep dive on your multi-sensor fusion implementation for a specific object detection or tracking problem
2 How you would approach curating datasets for rare obstacle types that don't appear frequently in training data
3 Transformer architecture optimization questions specific to perception tasks and latency constraints
4 Discussion of model deployment challenges on autonomous vehicle hardware and your experience with latency optimization
5 Scenario-based questions about handling extreme weather conditions or complex urban driving situations
Practice Interview Questions →

⚠️ Common Mistakes to Avoid

  • Only discussing academic ML projects without showing industry deployment experience or real-world constraints
  • Being vague about multi-sensor fusion experience - not specifying which sensors or fusion techniques you've used
  • Focusing only on model accuracy without addressing latency optimization or deployment considerations

📅 Application Timeline

This position is open until filled. However, we recommend applying as soon as possible as roles at mission-driven organizations tend to fill quickly.

Typical hiring timeline:

1

Application Review

1-2 weeks

2

Initial Screening

Phone call or written assessment

3

Interviews

1-2 rounds, usually virtual

✓

Offer

Congratulations!

Ready to Apply?

Good luck with your application to Zoox!

← Back to Job Listing Apply Now →