We are seeking a highly skilled Machine Learning Engineer with deep expertise in developing Bird’s Eye View (BEV) fusion models using multimodal sensor inputs, particularly LiDAR. You will play a central role in designing scalable perception algorithms that integrate data from camera, LiDAR, and radar sensors to support autonomous driving and 3D scene understanding.
Responsibilities:
- Design, implement, and optimize BEV-based perception models that fuse camera, LiDAR, and radar inputs.
- Benchmark perception models using large-scale datasets and well-defined quantitative metrics.
- Collaborate cross-functionally with research, data, and deployment engineers to refine models and support real-world applications.
- Maintain a strong focus on performance, robustness, and scalability for deployment in production systems.
- Ensure that your work is performed in accordance with the company’s Quality Management System (QMS) requirements and contribute to continuous improvement efforts.
- Ensure team compliance with QMS, monitor quality, and drive process improvements.
Required Skills:
- Ph.D. or Masters in AI, Computer Science, Electrical Engineering, Robotics, or a related field.
- Ph.D. new grad or Masters + 3 years industry experience
- Proficiency in Python and experience building deep learning pipelines.
- Strong expertise in PyTorch, TensorFlow, or JAX.
- Proven experience with LiDAR-based 3D perception and BEV representation models
- Deep understanding of multimodal sensor fusion architectures and techniques.
- Familiarity with camera, LiDAR, and radar modalities and their synchronization, calibration, and integration in perception pipelines.
- Solid foundation in computer vision, deep learning, and 3D geometry.
Preferred Skills:
- Industry or academic experience in autonomous vehicle perception, robotics, or related areas.
- Hands-on experience developing deep learning models in real-world or production environments.
- Experience with distributed training, high-performance computing, or GPU acceleration.