SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 150,000 - 240,000 / annual
Anyware Robotics builds general-purpose mobile manipulator robots for industrial applications, serving logistics, retail, and manufacturing with solutions for truck unloading, mobile palletizing, and machine tending. The company's robots run on AnywareOS, a modular industrial physical intelligence system designed to generalize across applications without reprogramming.
As Senior AI Perception Engineer, you will advance Anyware's production 3D AI perception stack for warehouse automation robots, focusing on object localization, pose estimation, and scene reconstruction. This role requires someone who has taken AI perception from prototype through production and real-world operation, making pragmatic tradeoffs across research potential, accuracy, reliability, latency, compute, data, maintainability, and delivery timelines.
Key responsibilities include:
- Advancing AI perception capabilities end-to-end: problem definition, prototyping, deployment, monitoring, failure analysis, and production improvement
- Developing and improving robust 3D perception algorithms for object localization, pose estimation, scene reconstruction, and manipulation using RGB-D and other sensing modalities
- Making engineering tradeoffs across accuracy, robustness, latency, compute cost, data availability, maintainability, and delivery timelines
- Improving perception reliability on physical robots by diagnosing failures from difficult scenes, lighting changes, sensor noise, and training-to-deployment gaps
- Strengthening production readiness through better data pipelines, evaluation, regression testing, release criteria, observability, and systematic field-failure analysis
- Collaborating across robotics teams to integrate perception into planning, manipulation, controls, and system software workflows
- Providing senior technical leadership through architecture decisions, design reviews, incident investigations, and mentoring
Required qualifications: MS or PhD in Robotics, Computer Vision, Computer Science, or related field; 3+ years developing robotic perception systems with direct responsibility for production deployment on physical robots; strong Python/C++ for real-time pipelines using ROS/ROS2; solid 3D geometry, camera models, calibration, RGB-D/point-cloud processing, and 3D localization/segmentation/pose estimation; hands-on AI model development (PyTorch) and deployment under latency/compute constraints; experience building production data pipelines, regression tests, observability, and root-cause analysis.
Nice-to-have: data flywheels, hard-example mining, model monitoring, multi-sensor fusion, edge GPU optimization (TensorRT, ONNX, CUDA, quantization), Isaac Sim/synthetic data/sim-to-real workflows, warehouse/logistics deployment experience.
Anyware's team has won six Best Paper Awards including ICRA 2025 and 2024. The company's robot Pixmo won Best Innovation at ProMat 2025 and MODEX 2026, plus the RBR50 Robotics Innovation Award. Perception work ships to real customer sites and directly impacts robot reliability and throughput under real-world variation.
