Machine Learning Engineer - Mapping

As a Machine Learning Engineer at our company, your primary responsibilities include designing and developing novel algorithms for 2D/3D machine perception, leveraging our extensive ML infrastructure to enhance model deployment, staying abreast of the latest research in machine learning and computer vision, and coordinating cross-functional initiatives to collaborate effectively with teams like Mapping and Data Science.

To qualify for the Machine Learning Engineer position in Foster City, CA, candidates should ideally possess a BS, MS, or PhD in Computer Science, Mathematics, or a related field. Additionally, having 3+ years of experience in relevant roles, proficiency in Python, and familiarity with deep learning frameworks like PyTorch are crucial for success in this role.

Compensation for the Machine Learning Engineer role varies based on experience, geographic location, and skills, generally ranging from $196,000 to $246,000. In addition to salary, the package includes Amazon Restricted Stock Units (RSUs), Zoox Stock Appreciation Rights, and a sign-on bonus, alongside a comprehensive benefits package that covers health insurance, paid time off, and more.

For a Machine Learning Engineer focused on high-definition maps, essential technical skills include experience in training and deploying deep learning models, a strong grasp of 3D computer vision, proficiency with projective geometry, and familiarity with tools for object detection and semantic segmentation. Knowledge of HD mapping and technologies such as SLAM or Structure from Motion (SFM) is particularly beneficial.

Machine Learning Engineers at our company have numerous growth opportunities, including continuing education in cutting-edge machine learning and computer vision technologies, potential leadership roles in cross-functional projects, and active participation in research that might lead to conference publications in notable venues such as CVPR, NeurIPS, and ICML.

When answering this question, highlight specific projects where you developed or deployed deep learning models. Discuss the frameworks you used, challenges faced, and how these experiences improved your skills and understanding of the subject.

Explain your methods, such as following relevant journals, attending conferences, or participating in online courses. Emphasize how you implement new learnings into your work.

Discuss the metrics you typically use, such as accuracy, precision, recall, or F1-score. Provide examples of how you’ve adjusted models based on these evaluations to improve performance.

Clearly articulate the role of 3D reconstruction in understanding environments for autonomous systems. Use examples from your work to demonstrate your understanding of its applications in navigation and mapping.

Emphasize your communication skills and provide examples of successful collaborations that resulted in project successes. Explain how you navigated conflicts and built consensus.

Discuss any practical experience you have working with HD maps, including projects that utilized this technology. Reflect on the challenges and solutions you encountered.

Talk about best practices you follow in coding and testing to ensure that models can be easily scaled. Mention experiences where you did this successfully in previous projects.

Explain your systematic approach to debugging, perhaps by starting from data integrity checks up to model evaluations. Illustrate your answer with a past situation where you effectively debugged a complex issue.

Use a specific example where you identified performance bottlenecks through metrics and made adjustments that led to measurable improvements. Quantify the impact if possible.

This is your chance to connect your personal values and career ambitions with the company’s mission. Share your enthusiasm for autonomous driving and the innovative environment our company offers to nurture your talent.