Staff ML Perception Engineer — Onboard Vision Systems

Latitude AI; Columbia Township (MI); On-site; USD 179,000 - 269,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Parental leave

Unlimited vacation

Job summary

Latitude AI is building the future of Ford’s autonomy roadmap to make travel safer, less stressful, and more enjoyable for everyone. We are developing an in-house hands-free ADAS platform that will debut on the Ford Fathom in 2027.

Latitude is a Ford Motor Company subsidiary with teams across Pittsburgh, Dearborn, and Palo Alto. The Unified Model team focuses on cutting-edge computer vision and ML to create multi-view, multi-sensor models for 3D object detection, lane detection, state

Qualifications

• Bachelor's or Master's degree in Computer Engineering, Computer Science, Electrical Engineering, Robotics, or related field.
• 7+ years of industry experience in ML or perception.
• Expert-level knowledge with PyTorch, TensorFlow or similar frameworks.
• Experience in perception systems using Camera, Radar, LiDAR and sensor fusion.

Responsibilities

• Develop spatio-temporal ML models for detection, fusion, segmentation.
• Analyze data and design state-of-the-art solutions.
• Transition lab results to test track and production environments.
• Collaborate with perception experts and roboticists on design, testing, and deployment.
• Maintain clean, scalable software practices for perception modules.
• Show initiative in a fast-paced, entrepreneurial setting.

Skills

Machine learning

Python

C++

Computer vision

Perception systems

PyTorch

TensorFlow

Sensor fusion

Education

Bachelor's or Master's in CS/EE/Robotics

Tools

PyTorch

TensorFlow

ROS

CUDA

Job description

Latitude AI is building the future of Ford’s autonomy roadmap to make travel safer, less stressful, and more enjoyable for everyone. We are developing an in-house hands-free ADAS platform that will debut on the Ford Fathom in 2027.

Latitude is a Ford Motor Company subsidiary with teams across Pittsburgh, Dearborn, and Palo Alto. The Unified Model team focuses on cutting-edge computer vision and ML to create multi-view, multi-sensor models for 3D object detection, lane detection, state