Bot Auto
GPU Engineer
Houston, TX or San Francisco Bay Area +1 · Full-time · Posted Aug 5, 2026
- Location
- Houston, TX or San Francisco Bay Area
Houston, Texas, United States - Experience
- 3+ years of GPU programming and optimization is preferred; no minimum years are specified as a requirement.
- Education
- Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related field.
About the job
Develop and optimize GPU software and onboard architectures for real-time autonomous-driving workloads, including sensor processing and neural-network inference.
What you'll do
- Optimize GPU performance, latency, throughput, resource use, and stability on embedded platforms.
- Develop parallel algorithms and GPU-accelerated components; profile and debug compute, memory, data movement, synchronization, and CPU–GPU bottlenecks.
- Collaborate on onboard GPU software architectures for perception, planning, and control.
What they ask for
- Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related field.
- Strong knowledge of parallel computing, GPU architecture, memory hierarchy, and performance optimization.
- Experience profiling GPU applications with NVIDIA Nsight Systems, Nsight Compute, or equivalent tools, and deploying or optimizing neural-network inference workloads.
- Experience with real-time embedded systems and sensor data streams; strong proficiency in C/C++ and Python.
Nice to have
- 3+ years of GPU programming and optimization experience.
- Experience with NVIDIA Jetson Thor, NVIDIA DRIVE Thor, model quantization, concurrent GPU workloads and resource isolation, or GPU-accelerated sensor data compression.
Tools
CUDA, NVIDIA Nsight Systems, Nsight Compute, PyTorch, ONNX, TensorRT, C/C++, Python
AI focus
Optimize neural-network inference workloads for autonomous driving, including sensor processing.
Model-written summary · the original posting is authoritative