Staff Robotics Perception Engineer - Real-World Autonomy

Simbe Robotics; San Francisco (CA); On-site; USD 190,000 - 240,000; Full time

Job summary

Simbe is redefining autonomous retail with robots and vision software. We seek a Principal or Staff Robotics Perception Engineer to own perception pipelines and translate perception models into reliable robot behavior in production environments.

You will improve navigation, localization, calibration, and customer facing intelligence on real-world store deployments. Join a team that bridges AI research, production CV, and robot software, and lead efforts in low-latency perception, edge inference,

Qualifications

• 7+ years of experience in robotic perception, computer vision, machine learning, autonomous systems, or related production robotics work.
• Strong proficiency in Python and C++ in Linux based development environments.
• Hands-on experience with ROS and/or ROS2, robot sensor pipelines, and deployed robotics systems.
• Experience with PyTorch, TensorFlow, ONNX, TensorRT, CUDA, or similar model training and inference tools.
• Demonstrated track record of adoption of LLM assisted and agentic programming techniques
• Strong understanding of object detection, segmentation, depth estimation, sensor fusion, calibration, visual localization, or SLAM.
• Experience deploying real time AI models on embedded systems, edge GPUs, robots, or other constrained hardware.
• Strong debugging, benchmarking, and systems thinking skills, with the ability to connect low level technical issues to product and customer outcomes.
• Ability to collaborate across Computer Vision, Robotics Software, Product, Customer Success, Field Operations, and executive stakeholders.

Responsibilities

• Own production perception pipelines. Lead the design, evaluation, integration, and optimization of perception systems used by Tally robots, including object detection, semantic and instance segmentation, depth estimation, tracking, sensor fusion, visual localization, and camera calibration.
• Bridge CV and robot autonomy. Partner with CV, Robotics Software, Product, and Field teams to integrate perception models into the robot codebase and improve navigation, localization, scene understanding, and system reliability.
• Improve real time performance. Profile and optimize neural networks on current and next generation robot hardware using Python, C++, ONNX, TensorRT, CUDA, and embedded GPU workflows.
• Advance robot perception R&D. Explore emerging techniques in visual SLAM, visual odometry, depth estimation, open vocabulary detection and segmentation, multimodal perception, and simulation to identify practical improvements.
• Develop system benchmarks. Define and maintain benchmarks that connect model quality to robot outcomes, including latency, compute, uptime, navigation success, localization robustness, false positives, false negatives.
• Debug field failures end to end. Use logs, robot data, imagery, maps, telemetry, and model outputs to diagnose perception and autonomy issues observed in production stores.
• Shape technical direction. Provide technical leadership, code reviews, architecture guidance, and mentorship for engineers working at the intersection of AI and robotics.

Skills

Python

C++

ROS/ROS2

Machine Learning

Computer Vision

SLAM/Localization

Edge Inference

Debug/Profiling

Cross-team collab

LLM assisted coding

Tools

PyTorch

TensorRT

CUDA

ONNX

Job description

Simbe is redefining autonomous retail with robots and vision software. We seek a Principal or Staff Robotics Perception Engineer to own perception pipelines and translate perception models into reliable robot behavior in production environments.

You will improve navigation, localization, calibration, and customer facing intelligence on real-world store deployments. Join a team that bridges AI research, production CV, and robot software, and lead efforts in low-latency perception, edge inference,