Senior Machine Learning Engineer - App Engine (CUDA)

Meet the Team

The mission of the Application Engine Team is to provide a robust, efficient, and flexible platform for integrating and managing various deep learning models and processes in the context of L4 autonomous trucking. It aims to streamline development workflows, enhance team efficiency, and ensure consistent performance and safety standards. The Application Engine focuses on facilitating the creation of scalable, reproducible, and safety-compliant components, enabling feature teams to efficiently develop and deploy advanced autonomous driving features.

What You’ll Do

• Design and implement advanced software solutions for distributed, GPU-based machine learning applications in autonomous driving.
• Develop and optimize message-passing pipelines across multiple System-on-Chips using Ethernet, PCIe, and other high-speed interconnects.
• Optimize concurrent resource usage (GPU, memory) to support parallel execution of deep learning models on embedded platforms.
• Build and maintain the runtime environment and SDK enabling deployment of ML-driven Virtual Driver applications.
• Collaborate with cross-functional teams to integrate App Engine capabilities into feature development pipelines.
• Author high-quality, production-ready C++ code and comprehensive test suites.

What You’ll Need to Succeed

• Bachelor’s degree in Computer Science, Electrical Engineering, or related field with 6+ years of experience, OR Master’s with 4+ years, OR PhD with 3+ years.
• Strong expertise in embedded software development with a focus on GPU programming.
• Proficiency in CUDA, TensorRT, and experience with machine learning frameworks (e.g., PyTorch).
• Experience designing and optimizing real-time distributed systems.
• Deep knowledge of modern C++ (C++14 or newer) and Linux development environments.
• Proven track record of delivering robust, maintainable, high-performance software in collaborative environments.

Bonus Points:

• Experience with PCIe data transport, low-level device interfaces, or high-speed networking.
• Exposure to safety-critical systems development.