Senior AI Software Engineer, Autonomous Systems

What you'll do

• Select and optimize AI models for autonomous applications to ensure scalability and low latency in edge and cloud environments.
• Integrate AI frameworks into software stacks while optimizing inference pipelines for real-world use cases.
• Provide technical leadership on deep learning frameworks, GPU-accelerated computing, and model compression strategies.
• Analyze and optimize AI software stack performance specifically for real-time inference and autonomous navigation.
• Implement model profiling, benchmarking, quantization, pruning, and distillation to improve performance and efficiency.
• Develop and optimize GPU kernels and manage memory using ROCm or CUDA programming.
• Profile end-to-end system performance using tools like NVIDIA Nsight, TensorRT, or Triton Inference Server.
• Deploy AI models within software stacks including ROS/ROS2 and edge AI hardware platforms.

What we're looking for

• Bachelor's or Master's degree in Electrical Engineering, Computer Engineering, Computer Science, or a closely related field.
• Experience designing and implementing solutions using PyTorch, TensorFlow, JAX, or ONNX Runtime (preferred).
• Knowledge of model profiling, benchmarking, quantization, pruning, and distillation techniques (preferred).
• Expertise in ROCm or CUDA programming, GPU kernel optimization, and GPU memory management (preferred).
• Proficiency in profiling tools such as NVIDIA Nsight, TensorRT, Triton Inference Server, or similar platforms (preferred).
• Experience deploying AI models with ROS/ROS2, real-time systems, and edge AI hardware like NVIDIA Jetson (preferred).
• Strong problem-solving skills for debugging complex AI model behavior and hardware-software interactions.
• Ability to work collaboratively in cross-functional teams with strong written and verbal communication skills.