1 month ago
Houston, TX, USA or San Francisco, CA, USAMid Level
Responsibilities
- Optimize end-to-end GPU performance for real-time autonomous driving workloads, including camera and LiDAR processing and neural network inference.
- Develop and optimize parallel computing algorithms and GPU-accelerated components using CUDA.
- Design and improve onboard GPU software architectures for perception, planning, and control modules.
- Profile and analyze bottlenecks in GPU computation, memory access, data movement, synchronization, and CPU–GPU interaction.
- Debug and optimize GPU-based software to improve latency, throughput, resource utilization, and runtime stability on embedded platforms.
- Collaborate with software engineers, AI researchers, and hardware specialists on high-performance autonomous driving solutions.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related field.
- Strong knowledge of parallel computing principles, GPU architecture, memory hierarchy, and performance optimization techniques.
- Experience profiling GPU applications with NVIDIA Nsight Systems, Nsight Compute, or equivalent tools.
- Experience deploying or optimizing neural network inference workloads using PyTorch, ONNX, and TensorRT.
- Experience with real-time embedded systems and large sensor data streams from cameras, LiDAR, and radar.
- Strong proficiency in C/C++ and Python.
- Preferred: 3+ years of experience in GPU programming and optimization using technologies such as CUDA, OpenCL, or Vulkan.
- Preferred: Experience with NVIDIA Jetson Thor, NVIDIA DRIVE Thor, or similar embedded GPU platforms.
- Preferred: Experience with model quantization, including FP8 and NVFP4.
- Preferred: Experience managing concurrent GPU workloads and resource isolation using NVIDIA MPS, MIG, or related technologies.
- Preferred: Experience with GPU-accelerated sensor data compression.
Categories
About Bot Auto
Bot Auto runs autonomous trucks out of Houston, Texas. We sell the capacity, not the technology. We own the trucks, the safety case, and the operation end to end. Our team pairs trucking operators who've run real fleets with the engineers building the technology because commercializing this industry takes both. We're not chasing a demo. We're building the freight network the industry actually needs.