What to ExpectWe are looking for a hands-on Perception Engineer who can build the system that allows our robot to understand people and the world around it. You will work on developing computer vision and machine learning system at the core of the robot's awareness, enabling it to recognize people, understand gestures, track attention, and respond naturally in real time. The liveliness of our robot will truly convey the character interface that we are building that can learn and adapt as required.
This role sits at the intersection of robotics, machine learning, and software engineering. You will work closely with the CEO and the founding team to develop perception capabilities from prototype to deployment, collecting data, training models, optimizing performance, and integrating the stack directly into the robot's behavior.
In this Role, You Will:- Design, train, and deploy computer vision and perception models for person detection, tracking, pose estimation, gesture recognition, emotion recognition and scene understanding.
- Develop data collection, labeling, and evaluation pipelines to improve model performance and reliability.
- Build perception systems that operate robustly across varying lighting conditions, environments, and user behaviors.
- Optimize models for real-time inference on edge hardware while balancing latency, accuracy, and power constraints.
- Work with RGB cameras, depth sensors, IMUs, audio inputs, and other sensor modalities to create multi-modal perception systems.
- Develop tools for dataset management, model evaluation, debugging, and monitoring.
- Support integration between perception, behavior, controls, and firmware systems.
- Stay updated with state-of-the-art research to develop architectures and techniques that can improve the robot's ability to understand and interact with people.
- Debug perception failures systematically and close the loop through data-driven improvements.
- Help define and evolve the platform's perception architecture as the robot grows in capability.
You May Be a Good Fit If You:- Have a degree in Computer Engineering, Computer Science, Robotics, Electrical Engineering, or a related field, and a minimum of 3+ years of hands-on experience.
- Are proficient in Python and comfortable working in C++ when required.
- Have experience training and deploying machine learning models using frameworks such as PyTorch, TensorFlow, ONNX, or similar tools.
- Have worked on computer vision problems such as object detection, tracking, pose estimation, segmentation, gesture recognition, or activity understanding.
- Have experience deploying models to edge devices and optimizing performance for real-world systems.
- Understand the challenges of collecting, labeling, and maintaining high-quality datasets.
- Are comfortable working in environments where architecture is still evolving and your input shapes direction.
- Document clearly and drive issues to resolution.
You Will Be a Strong Fit If You:- Care deeply about building perception systems that work reliably outside ideal lab conditions.
- Have strong intuition for debugging machine learning systems and can distinguish between data problems, model problems, and deployment problems.
- Enjoy converting cutting-edge research into practical systems that ship.
- Think critically about tradeoffs between accuracy, latency, robustness, power consumption, and cost.
- Have the ability to quickly adapt through iteration cycles without waiting for perfect information to make progress.
- Take ownership over systems end-to-end, from data collection and training through deployment and monitoring.
- Work well in small, collaborative teams where software, hardware, controls, and AI are in constant conversation.
- Care about what perception enables: awareness, responsiveness, and the feeling that the robot is alive.
The early team becomes the DNA of the company. We set ourselves and others to a high standard, and we respond with kindness when things get hard but keep everyone accountable. This requires us to be curious, creative, and diverse in our thinking and approach.
