Job Summary:
Sunday is developing personal robots to reclaim the hours lost to repetitive tasks, aiming to make generalized robots broadly accessible. They are seeking a System Software Engineer focused on GPU and accelerated compute to own the accelerated compute layer of their ML & Robotics Infra, ensuring efficient model execution and GPU scheduling for real-time robotic systems.
Responsibilities:
โข Youโll own and contribute to the accelerated compute layer of the ML & Robotics Infra, including:
โข Efficient model execution and switching: Reduce gpu kernel launch overheads and make swapping between models on the same device fast and predictable
โข GPU scheduling and time-slicing: Arbitrate GPU access across concurrent users (model inference, SLAM, and other robotics applications) with predictable latency
โข Camera pipeline: Drive low-latency transfer of camera frames into GPU memory, integrating with HW accelerate encode/decode (NVDEC/NVENC) where appropriate
โข CPU โ GPU data transfer: Build efficient, low-overhead data movement between host and device, including pinned memory, zero-copy paths, and asynchronous transfer patterns
โข CPU/GPU synchronization: Design synchronization primitives and patterns that minimize stalls and keep inference pipelines full
Qualifications:
Required:
โข 2+ years of experience developing gpu systems software
โข Strong proficiency in CUDA and a systems language such as C++, C, or Rust
โข Solid understanding of GPU architecture, GPU workloads, and the tradeoffs involved in time-slicing and sharing the device across users
โข Hands-on experience with the CUDA ecosystem: CUDA runtime API, CUDA Graphs, and CUDA IPC
โข Familiarity with GPU sharing mechanisms such as MPS and MIG
โข Experience with GPU profiling tools such as Nsight Systems and Nsight Compute
โข Solid Linux fundamentals: scheduling, IPC, memory management, and performance tuning
Preferred:
โข Contributions to CUDA libraries or other GPU programming libraries
โข Experience with camera pipeline integration and NVDEC/NVENC
โข Experience optimizing model inference on embedded GPU platforms (e.g., Jetson)
โข Experience with observability and tracing for GPU-accelerated workloads
Company:
Sunday is a robotics and artificial intelligence company that develops an autonomous home robot to assist with household tasks. Founded in 2024, the company is headquartered in Mountain View, USA, with a team of 51-200 employees. The company is currently Early Stage.