This position, posted by Jobgether on behalf of a partner company, is looking to solve the business and technical problem of developing machine learning models for autonomous vehicle perception, specifically for road and lane detection in complex environments. The goal is to optimize algorithms for real-world deployment, influencing vehicle navigation and safety.
Requirements
- Strong expertise in 3D BEV space modeling, lane and road geometry, multi-camera calibration, and sensor projection
- Proficiency in Python and PyTorch, with experience translating research code into production-ready systems
- Hands-on experience with multi-modal sensor data (camera, LiDAR, radar) and data management pipelines
- Experience deploying and optimizing ML models for embedded and real-time systems
- Preferred: PhD in ML or Data Science
- Preferred: CUDA programming
- Preferred: custom PyTorch operations
Responsibilities
- Develop and optimize computer vision algorithms for road and lane detection in monocular and multi-modal contexts
- Design and implement deep learning models for BEV (bird’s eye view) representations integrated into planning and control pipelines
- Analyze model performance, data distributions, and edge cases using advanced data science techniques
- Build efficient pipelines for large-scale data processing, annotation, augmentation, and domain adaptation
- Deploy and optimize ML models for real-time inference on automotive-grade hardware
- Collaborate cross-functionally with robotics, software, hardware, product, and operations teams to ensure seamless system integration
- Mentor junior engineers and contribute to the technical roadmap, staying current with the latest advancements in ML and computer vision
Other
- Bachelor’s degree with 6+ years or Master’s degree with 3+ years of professional experience in Machine Learning Engineering, Autonomous Vehicles, Robotics, or a related field
- Strong analytical, problem-solving, and communication skills, with a track record of mentoring or leading technical teams
- Preferred: publications in top-tier ML/Computer Vision conferences
- Preferred: experience with distributed training and multi-GPU systems
- Hybrid or remote work options available in the United States
