Senior/Principal Engineer - Tracking

The Tracking team owns the car's multi-object tracking (MOT), which uses deep learning methods to improve the spatio-temporal consistency of Perception output. More specifically, we use multi-modal Transformer models to perform sensor fusion, data association, state estimation, ReID, occlusion reasoning, etc. The team owns the Tracker’s full development cycle, from ideation, experimentation, validation, simulation, in-vehicle testing, and final deployment into production. We are looking for engineers who are passionate about Level 5 autonomous driving, excited by intellectual challenges,  and interested in pursuing career growth with a fast-growing company. 

Motional's Machine Learning team has produced groundbreaking advancements in the autonomous vehicle industry, including nuScenes (https://www.nuscenes.org), PointPillars (https://arxiv.org/abs/1812.05784), PointPainting (http://arxiv.org/abs/1911.10150) and end-to-end MOT by MotionTrack (https://arxiv.org/abs/2306.17000).

What You’ll Be Doing:  

• Lead the effort of cutting-edge MOT systems with Machine Learning and optimization-based methods
• Use your top-notch software development expertise to inspire others to develop better software practices and principles
• Design and build a robust and scalable codebase that enables rapid exploration and evaluation of different MOT approaches and algorithms
• Interface with perception and prediction components upstream and trajectory optimization and tracking & control components downstream
• Evolve the data-driven model according to the performance of AV in real-world complex environment.
• Own the end-to-end product development cycle and drive the impact across the organization.
• Guide and mentor junior team members to develop a culture of product-focused engineering, research, and development.

Senior Engineer:

• Develop a variety of algorithms for Tracking for autonomous driving, including but not limited to data association, camera-lidar fusion, state estimation, ReID, occlusion reasoning, nonlinear Kalman filtering
• Lead and Develop core deep learning algorithms for efficient training and testing pipelines
• Deploy solutions directly to an autonomous vehicle and analyze their impact 
• Drive goal achievement for the Tracking team consistently 

Principal Engineer:

• Define technical roadmap for cutting-edge MOT systems with Machine Learning and optimization-based methods
• Lead cross-team effort and develop a variety of algorithms for Tracking for autonomous driving, including but not limited to data association, camera-lidar fusion, state estimation, ReID, occlusion reasoning, nonlinear Kalman filtering.
• Contribute toward building a high-performing team, and serves as a role model to people around you in at least one technical area and one behavioral area
• Provide a vision for the Tracking team and surrounding teams

What We’re Looking For:

• Bachelor's, Masters, or PhD degree preferred in Machine Learning, Robotics, Computer Science, Computer Engineering, Mechanical Engineering, Applied Mathematics, Statistics, or a related field
• Experience designing, training, analyzing, and deploying neural networks with PyTorch or other deep learning frameworks
• Experience owning and leading technical development on features from problem formulation through implementation and deployment
• Growth mindset and continuous innovation

Senior Engineer:

• 3+ years of software development experience 
• 2+ years of Deep Learning product development experience preferred
• 1+ years of C++ software development experience preferred
• Strong track record of tackling less well-defined problems, and executing efficiently to deliver the successful outcome
• Experience mentoring and collaborating with others

Principal Engineer:

• 7+ years of software development experience 
• 4+ years of Deep Learning product development experience preferred
• 2+ years of C++ software development experience preferred
• Effectiveness at leading and executing large, complex technical initiatives 
• Strong track record of tackling ambiguous problems, creating clarity from it, and driving it to successful outcomes

Bonus Points:

• Proven track record of publications in relevant conferences (CVPR, ICML, NeurIPS, ICCV, CoRL, IROS, ICRA, etc.)
• Ph.D. in machine learning, computer vision, or robotics
• Experience working on autonomous vehicles, or related fields
• Experience in deploying models into real-world environments
• Strong programming skills in C++ and/or CUDA programming