Senior, ML Engineer - 3D Reconstruction

Role Description

The Pseudo-Labeling team's goal is to create high-quality annotations on sensor data (images, point clouds). The annotations include:

• 2D, 3D bounding boxes
• Classes
• Trajectories
• Lane lines
• Segmentations
• Depths
• High-definition map elements

These annotations are used by different downstream users, such as:

• Perception teams for training various models
• Mapping teams for building and maintaining HD maps
• Simulation teams for generating new data

What You’ll Do:

• Design, implement, test and deploy offline 3D reconstruction, lane line detection, and automatic mapping/map creation modules.
• Build and refine lane line annotation pipelines using the latest machine learning models.
• Develop and improve pose estimation algorithms for accurate localization and 3D scene reconstruction.
• Demonstrate project management skills, serving as project lead.
• Stay updated with developments in AI and ML for autonomous driving.
• Independently develop offline perception and mapping models or algorithms.
• Define and implement ingestion, data preparation, curation, and governance of large data sets.
• Proactively assess current capabilities and propose improvements.
• Measure and track auto-labeling and map creation quality.
• Guide and produce information products for visualization and data accessibility.
• Evaluate technical advances to improve productivity and quality.
• Develop guidelines and standards for analytics and machine learning models.
• Provide technical guidance, leadership, coaching, and mentoring to team members.

Qualifications

• Highly skilled and proficient in discipline; conducts complex work under minimal supervision.
• Expected to drive alignment across team interfaces.
• Mentors and guides engineers within the group.
• Bachelor’s Degree in Computer Science, Robotics, Electrical Engineering or related field plus 6+ years of experience OR;
• Master’s Degree in relevant field plus 3+ years of experience.

Requirements

• Experience in lane line annotation creation or automatic mapping/map creation.
• Familiarity with the latest lane line detection and creation machine learning models.
• Familiarity with pose estimation.
• Active Learning & Pseudo-labeling – Computer Vision, Deep Learning, Model training.
• Two of the following: 2D/3D Object Detection, Tracking, Sensor Fusion, Semantic Segmentation, SLAM, BEV.
• Scaled ML Operations (MLOps) and Tooling – ML Frameworks, experiment tracking, model registry.
• Distributed machine learning frameworks – PyTorch, Lightning, Ray.
• Model Data Curation – Parquet data processing.
• Proficiency in Python software development and cloud-based development environments.

Benefits

• A competitive compensation package including a bonus component and stock options.
• 100% paid medical, dental, and vision premiums for full-time employees.
• 401K plan with a 6% employer match.
• Flexibility in schedule and generous paid vacation.
• Company-wide holiday office closures.
• AD+D and Life Insurance.