Senior, ML Engineer - 3D Reconstruction
$199k - $299k • Remote • Remote - US, Ann Arbor, MI • Full-time
Posted 11mo ago
This job has been open for more than 60 days. It may no longer be actively hiring, so check with the company before putting a lot into an application.
Job Location
Remote - US, Ann Arbor, MI
Tech Stack
Remote Work Policy
Fully remote
Employment Type
Full-time
Categories
Machine Learning Engineer
About the job
Torc is seeking a Senior ML Engineer to join the Pseudo-Labeling team, focusing on creating high-quality annotations from sensor data for autonomous vehicle development. This role will own critical challenges in lane line reconstruction and mapping, setting technical direction for lane line accuracy, map creation, and pose accuracy. You will be responsible for designing, implementing, and deploying systems that generate annotations from logged sensor data, leading efforts in lane line network reconstruction, and developing models for map creation and updates. The position also involves owning pose correction for sensor data and diagnosing calibration/sensor errors. You will act as a technical lead on complex projects, mentor other engineers, and stay abreast of the latest AI/ML advancements in autonomous driving and 3D reconstruction, bringing new techniques into production. This role requires independent development of models and algorithms using disciplined software processes, defining data ingestion and governance, and assessing current capabilities for improvement.
Responsibilities
- Design, implement, and deploy offline 3D reconstruction, lane line detection, and automatic mapping systems.
- Lead lane line network reconstruction efforts, rebuilding topologically correct lane line graphs.
- Design, train, and iterate on lane line detection and creation models.
- Develop methods for creating lane line maps in unmapped areas and handling map updates.
- Own pose correction for sensor data and lead diagnosis/mitigation of calibration/sensor errors.
- Set technical direction and best practices for lane line, mapping, and pose estimation pipelines.
- Serve as technical lead on high-complexity projects, guiding and mentoring engineers.
- Develop offline perception and mapping models or algorithms using disciplined software development processes.
- Define and implement ingestion, data preparation, curation, and governance of large datasets.
- Measure and track auto-labeling and map creation quality.
- Evaluate and recommend technical advances to improve productivity and quality.
- Develop guidelines and standards for analytics and machine learning models and their deployment.
Requirements
- Expertise and high skill in discipline, conducting complex work independently.
- Ability to drive alignment across team and organizational boundaries.
- Sets technical direction, owns team technical solutions end-to-end.
- Mentors and guides engineers within and beyond the group.
- Bachelor’s Degree in Computer Science, Robotics, Electrical Engineering or related technical field plus 6+ years of experience; OR Master’s Degree plus 3+ years of experience; OR PhD plus 1+ years of experience.
- Strong background in lane line detection and creation, including network reconstruction and model training.
- Proven experience creating lane line maps for unmapped areas and handling map updates.
- Strong background in pose correction, with experience diagnosing and correcting calibration/sensor errors.
- Expertise in Active Learning & Pseudo-labeling, Computer Vision, Deep Learning, and advanced model training.
- In-depth experience with at least two of the following: 2D/3D Object Detection, Tracking, Sensor Fusion, Semantic Segmentation.