Research Engineer, Computer Vision

We are seeking a Research Engineer to join the Localization & Mapping team at Plus, focusing on the design, development and deployment of software to advance our self-driving technology. The primary focus of the role is scene reconstruction and auto labeling of the urban driving scenes.

You'll collaborate with a diverse team of researchers and engineers on core topics in computer vision, deep learning and optimization. You'll design and implement state-of-the-art algorithms in making a scalable auto labeling/mapping process, delivering significant impact to the company and the autonomous driving industry.

Responsibilities

• Develop 3D visual reconstruction of highway and urban driving scenarios including static scenes and dynamic objects
• Identify unique and high-value driving scenes to maximize data labeling efficiency, class distribution imbalance (long-tail) challenges in autonomous driving
• Develop a distributed and automated pipeline for large scale scene reconstruction and automatic label generation
• Curate high-quality dataset for autonomous driving scenarios and design robust evaluation metrics
• Contribute to state-of-the-art perception/LLM models for perception for automated driving
• Collaborate with engineering teams including perception, prediction, planning and data infrastructure to integrate auto labeling and auto mapping pipeline for broader use
• Ensure that your work is performed in accordance with the company’s Quality Management System (QMS) requirements and contribute to continuous improvement efforts
• Ensure that technical work meets customer requirements, regulatory standards, and company quality policies.

Required Skills:

• MS or PhD in Computer Science, Electrical Engineering, Robotics, similar technical field of study, or equivalent practical experience
• Software design and development experience in Python and C++
• Experience in 3D computer vision
• Experience with training/fine tuning deep learning networks(CNN, Transformers, etc)

Preferred Skills:

• 2-3 years of industry experience in a relevant role
• Project experience with Structure from Motion
• Experience and/or knowledge of NERF/Gaussian Splatting
• Experience in optimization with ceres 
• Experience with VLM networks
• Basic understanding of multi processing/threading
• Publication record in relevant venues (CVPR, ICLR, ICCV, ECCV, NeurIPS, AAAI, SIGGRAPH, ICRA, IROS, etc.)

Salary Range:

• $120,000 - $200,000 a year

Our compensations (cash and equity) are determined based on the position, your location, qualifications, and experience.