ML Engineer, II - Multi Modal Fusion

What you'll do: 

• Contribute to the development and deployment of machine learning models for autonomous trucking, focusing on creating an accurate static and dynamic scene model of the environment around the ego vehicle. 

• Develop and optimize deep learning models and classical tracking algorithms for real-time static and dynamic scene modeling of the environment under the guidance of senior engineers.  

• Assist with model optimization for improved performance and efficiency. 

• Contribute to the deployment of perception models and components onto the truck platform. This includes:  

• Assisting with optimizing model inference speed and memory usage for real-time performance on embedded systems with limited resources. 

• Contributing to the design and implementation of data pipelines for model training and deployment. 

• Supporting the integration of the perception system with the truck's hardware and software infrastructure. 

• Assist with the development and deployment of monitoring and diagnostics tools to track model performance and components over time and identify potential issues. 

• Collaborate closely with other engineers to integrate the software components with the rest of the perception stack. 

• Participate in rigorous testing and evaluation of the perception system in simulation and real-world trucking environments, analyzing performance metrics. 

What you’ll need to Succeed: 

• BS in Computer Science, Robotics, or related fields with 4+ years of relevant work experience or a Master’s with 2+ years of experience. 

• Experience in deploying neural network architectures in a constrained environment. 

• Proficiency in Python with familiarity with deep learning frameworks like PyTorch or TensorFlow. 

• Strong proficiency in C/C++ for algorithm development and system integration. 

• Experience with basic model optimization techniques is a plus. 

• Familiarity with version control systems (e.g., Git) and agile development methodologies