> Markdown version of [/jobs/ext/3555881-system-architect-compute-platform-navigation-embodied-ai-robotics](https://www.wearedevelopers.com/jobs/ext/3555881-system-architect-compute-platform-navigation-embodied-ai-robotics). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # System Architect - Compute Platform, Navigation & Embodied AI, Robotics - **Company:** Insight Global - **Location:** Austin, TX, United States - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Computing Platforms, C++ (Programming Language), Computer Engineering, Firmware, Global Positioning Systems (GPS), Python (Programming Language), Motion Planning, Open Source Technology, Sensor Fusion, Systems Architecture, Discretization, Isaac Sim, Embodied AI, Information Technology, ONNX (Open Neural Network Exchange) Format, Machine Learning Operations, Model Inference, Lidar - **Published:** October 2, 2026 - **Apply:** https://dejobs.org/x/x/6354641CFF49454D8B77DBE5CC73F181/job/ ## About the Role * 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) ## Description 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 ## Related Videos - [Enhancing AI-based Robotics with Simulation Workflows](https://www.wearedevelopers.com/videos/472-enhancing-ai-based-robotics-with-simulation-workflows) - [Robots 2.0: When artificial intelligence meets steel](https://www.wearedevelopers.com/videos/1452-robots-2-0-when-artificial-intelligence-meets-steel) - [How to develop an autonomous car end-to-end: Robotic Drive and the mobility revolution](https://www.wearedevelopers.com/videos/22-how-to-develop-an-autonomous-car-end-to-end-robotic-drive-and-the-mobility-revolution) - [Playing Pong on a shoulder press machine](https://www.wearedevelopers.com/videos/100140-playing-pong-on-a-shoulder-press-machine) - [Physical AI for the Next Wave of Industrial Digitalisation](https://www.wearedevelopers.com/videos/100039-physical-ai-for-the-next-wave-of-industrial-digitalisation) - [How Robots Learn to be Robots](https://www.wearedevelopers.com/videos/1632-how-robots-learn-to-be-robots) ## Related Articles - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [ I Gave a Video Editor More Autonomy Than a Trading Bot. On Purpose.](https://www.wearedevelopers.com/magazine/773-i-gave-a-video-editor-more-autonomy-than-a-trading-bot-on-purpose) - [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere) - [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)