System Architect - Compute Platform, Navigation & Embodied AI, Robotics

We are seeking a System Architect for Compute Platforms targeting Navigation and Manipulation in robotics. This role defines the hardware and software compute stack enabling robots to perceive, navigate, and manipulate in unstructured environments. The architect drives architecture of heterogeneous compute platforms (application processors, NPUs, vision accelerators) and the software stacks spanning SLAM/VSLAM, Visual Language Action models (VLAs), manipulation planning, and sensor fusion running on silicon.

Key Responsibilities Compute Platform Architecture * Define heterogeneous SoC platform architecture (NPU/GPU accelerators, LPDDR5/HBM) for perception, planning, and control workloads * Specify hardware accelerator requirements for transformer/CNN inference, point cloud processing, and dense depth estimation Navigation Stack - SLAM / VSLAM * Architect VSLAM pipelines (stereo, RGB-D, event cameras, LiDAR): ORB-SLAM3, RTAB-Map, LIO-SAM, Cartographer) * Define sensor fusion for localization: VIO (visual-inertial odometry), IMU pre-integration, UWB/GPS * Specify occupancy mapping and motion planning stacks (A*, MPPI, TEB) adapted for legged humanoid locomotion Manipulation Stack & VLAs * Architect VLA inference pipelines (RT-2, OpenVLA, pi0) for language-conditioned manipulation; define latency budgets * Specify 6-DoF grasp detection and pose estimation (GraspNet, FoundationPose) and whole-body loco-manipulation planning * Evaluate Sim2Real transfer frameworks (Isaac Sim, MuJoCo, Genesis) for HIL validation flows

• 8+ years in AI/ML systems engineering, robotics system design is a plus * Heterogeneous compute: ARM application processors, NPUs, GPU/vision accelerators * SLAM/VSLAM: hands-on implementation on embedded/edge platforms * VLA / foundation models: RT-2, OpenVLA, Octo, pi0; inference hardware requirements and optimization * AI inference runtimes: ONNX Runtime, TFLite, quantization/pruning * ROS 2, Python, C++; simulation (Isaac Sim, MuJoCo, Gazebo, Genesis) * Proven ability to define compute platform architecture across hardware, firmware, and software teams * Experience engaging with robotics OEMs, AI research labs, and open-source communities * Bachelor’s in EE, Computer Engineering, Computer Science, or Robotics (required)