Senior Software Engineering Manager - Multi-Object Tracking & State Estimation

Experience developing and shipping learned multi-object tracking systems

Experience with classical state estimation methods, such as Kalman filters (and varieties thereof), particle filters, etc

Significant experience with Python and/or C++

Proven track record of shipping machine learning-based solutions to computer vision problems using PyTorch or similar (TensorFlow, JAX, etc)

with focus on machine learning, or equivalent experience

Track record of shipping end to end computer vision systems

High-quality individual and family medical, dental, and vision insurance

Health savings account with available employer match

Employer-matched 401(k) retirement plan with immediate vesting

Employer-paid group term life insurance and the option to elect voluntary life insurance

Paid parental leave

Paid medical leave

Lead a team of experts to deliver critical functionality for the next generation of autonomy systems at Ford.

This functionality includes (but is not limited to) multi-object tracking, estimation of the road properties (such as lane markings, road shape, topology, etc) over time, and pre-collision assist / automatic emergency braking

Stay current with literature, analyze current system performance, and design state of the art solutions with the team for the above goals.

Develop ML models in both a modular and E2E framework

Collaborate with expert roboticists and ML engineers and scientists to integrate and deploy State Estimation solutions into production.

Analyze failures and collaborate with systems engineering to develop verification and validation cases, and take ideas from concept into mass production

The State Estimation team is responsible for multi-object tracking and scene estimation, in both a classical physics-informed and modern ML sense. Collaborating with other ML teams, systems engineering, and product management, State Estimation builds advanced models that blend the best of the research literature with the needs of industry to estimate long-duration characteristics (e.g. kinematics, shape, etc) of both actors and road features. State Estimation is the interface of the perception system to various downstream autonomy consumers including motion planning, prediction, and localization. The team takes these algorithms and models from the lab to the road, and directly powers production grade perception systems on our vehicles.