Senior Machine Learning Engineer

What You'll Be Doing

• Model Development: Design, train, and optimize innovative machine learning models for LiDAR/camera perception and multi-sensor fusion (e.g., object detection/classification, image classification, semantic segmentation, tracking).
• Develop and coordinate entire ML workflows, covering data pipelines, model training, model metrics, continuous performance instrumentation, and reporting.
• Productization: Take ML models and algorithms from initial evaluation and experimentation all the way to product level on the NVIDIA DRIVE AV platform, developing highly efficient product code in C++.
• Innovation: Keep track of the latest developments in machine learning, and incorporate techniques that improve platform performance.
• Collaborate with LiDAR/camera teams, developers, engineers, and managers to turn complex ideas into reliable solutions for autonomous driving.

What We Need To See

• MS or PhD in Computer Science, Engineering, or a related field, or equivalent experience.
• 8+ years of relevant proven industry experience applying machine learning to address real-world problems.
• Strong C++ and Python programming and debugging skills with experience in developing for large, complex systems.
• Deep practical experience applying machine learning to lidar/camera perception and multi-sensor fusion in automotive or related fields.
• Experience with deep learning frameworks (e.g., PyTorch, TensorFlow) and a strong understanding of the mathematical foundations of ML.
• Building and sustaining training and essential metric workflows for large-scale datasets.
• Excellent communication and analytical skills. Self-motivated drive to solve hard problems.

Ways To Stand Out From The Crowd

• Multi-sensor fusion, LiDAR or Camera Perception Experience: Proven track record of developing and shipping deep learning models for LiDAR/Camera and Multi-Sensor Fusion in a production environment.
• Advanced Model Knowledge: Familiarity with modern network architectures like Transformers and their application to visual recognition tasks.
• AV Production Experience: A history of delivering ML features and models into a production autonomous vehicle stack or a related robotics product.
• Performance Optimization: Experience with model optimization for real-time inference on embedded or automotive platforms (e.g., using TensorRT).

Pay

Base salary range: 184,000 USD - 287,500 USD for Level 4, and 224,000 USD - 356,500 USD for Level 5. You will also be eligible for equity and benefits.