Senior Software Engineer, Unified Modeling, CVML

Latitude

full-time

Posted on: 8/26/2025

Location: California, Pennsylvania • 🇺🇸 United States

✨ AI Apply

💰 $174,000 - $261,000 per year

Senior

CloudPythonPyTorchTensorflow

About the role

Latitude AI develops automated driving technologies, including L3, for Ford vehicles at scale
Work alongside leading experts across machine learning and robotics, cloud platforms, mapping, sensors and compute systems, test operations, systems and safety engineering
Unified Model development team builds compute-efficient, multi-view, multi-sensor deep learning models for detection, segmentation, lane line detection, state estimation, and scene representation
Develop spatio-temporal machine learning models for detection, multi-sensor fusion, segmentation, etc.
Read literature, analyze raw data, and design state-of-the-art solutions
Transition solutions from the lab to the test track and public roads to ensure successful production-level implementation
Collaborate with perception experts and experienced roboticists on algorithm design, prototyping, testing, deployment, and productization
Build and maintain industry-leading software practices and develop clean and efficient perception software

A Bachelor's or Master's Degree in Computer Engineering, Computer Science, Electrical Engineering, Robotics, or a related field
Expert-level knowledge and experience in machine learning, with a proven track record of developing and deploying deep learning solutions using PyTorch, Tensorflow, or similar frameworks
Experience in developing perception systems using sensors such as Camera, Radar, and LiDAR
Strong experience in computer vision, perception, and point cloud processing
Proven experience in shipping computer vision software products to industry or consumers
At least 5 years of development experience in Python/C++ environments
Ph.D. with machine learning focus, or equivalent experience (nice to have)
Experience developing and deploying temporal computer vision models (for instance, video activity recognition or using multiple frames for improved results) (nice to have)