Bachelor's or Master's degree in Computer Science, Computer Engineering, Robotics, Electrical Engineering, or related field, or equivalent experience.
Strong programming skills in C++, including data structures, algorithms, and object-oriented programming.
Experience with CUDA and GPU programming, focusing on parallel execution and memory management.
Understanding of parallel and concurrent programming concepts, including multithreading and synchronization.
Familiarity with Python for scripting, testing, or machine learning workflows.
Understanding of reinforcement learning concepts, including environments, agents, actions, rewards, and training workflows.
Experience developing and debugging software in Linux.
Responsibilities
Build GPU-accelerated simulation software for autonomous driving and reinforcement learning.
Improve the throughput of parallel simulation workloads and their integration with training workflows.
Profile simulation and training workloads, optimizing CPU and GPU execution, memory usage, and data transfer.
Develop tests and benchmarks to measure correctness, performance, and reproducibility.
Collaborate with data, planning, and machine learning engineers on implementation, design discussions, and code reviews.
Benefits
Collaborative work environment with cross-functional teams.
Opportunity to work on cutting-edge technology in autonomous trucking.
Focus on performance optimization and innovative simulation techniques.
Engagement in meaningful projects that impact the future of transportation.
Full Job Description
We are looking for a software engineer with C++ and CUDA experience to develop GPU-accelerated simulation software and improve reinforcement learning training efficiency. You will work with data, planning, and machine learning engineers on simulation and training infrastructure for autonomous trucking. What You'll Do
Build GPU-accelerated simulation software for autonomous driving and reinforcement learning.
Improve the throughput of parallel simulation workloads and their integration with training workflows.
Profile simulation and training workloads, and optimize CPU and GPU execution, memory usage, and data transfer.
Develop tests and benchmarks to measure correctness, performance, and reproducibility.
Collaborate with data, planning, and machine learning engineers on implementation, design discussions, and code reviews.
Required Qualifications
Bachelor's or Master's degree in Computer Science, Computer Engineering, Robotics, Electrical Engineering, or a related field, or equivalent practical experience.
Strong programming skills in C++, including data structures, algorithms, and object-oriented programming.
Experience with CUDA and GPU programming, including an understanding of GPU parallel execution and memory management.
Understanding of parallel and concurrent programming concepts, including multithreading and synchronization.
Familiarity with Python for scripting, testing, or machine learning workflows.
Understanding of reinforcement learning concepts, including environments, agents, actions, rewards, and training workflows.
Experience developing and debugging software in Linux.
Strong problem-solving skills and ability to work collaboratively across teams.
Preferred Qualifications
Experience profiling or optimizing C++ applications, GPU workloads, or machine learning pipelines.
Familiarity with PyTorch or another machine learning framework.
Experience with simulation, robotics, game engines, physics, computational geometry, or high-performance computing.
Experience optimizing GPU kernels or multi-GPU workloads.
Exposure to batched environments, multi-agent systems, or distributed training.
Experience with testing tools, Git, and collaborative software development.
