Robotics Software Engineer

Summary

Salary:

Competitive

Job Family:

Product Software Engineering

Location:

Singapore - St James Power Station Headquarters

About Us

Dyson is a global technology company that sets out to solve the problems others ignore. We create machines that are different, better and more useful through inventive engineering, relentless testing and a refusal to accept conventional answers.

About the Role

As a Robotics Software Engineer, you will design and develop core robotics behaviours and features for intelligent products, contributing to high-performance, reliable, and scalable robotic systems. You will work within a cross-functional team to solve real-world robotics problems, particularly in navigation, perception, and autonomous behaviour.

Key Responsibilities

Design and develop robotics behaviours and features for embedded systems

Implement algorithms for navigation, control, and task execution in robotic platforms (e.g., vacuum robots)

Contribute to full software lifecycle: requirements, design, implementation, testing, and maintenance

Participate actively in feature design discussions and code reviews

Optimize system performance, robustness, and reliability

Collaborate with hardware, product, and testing teams

AI/ML Responsibilities

Implement and integrate ML models into embedded/edge robotics systems, ensuring efficient runtime performance (latency, memory, power constraints)

Support development of perception modules:

Object detection and classification (e.g., obstacles, floor types, dirt detection)

Basic scene understanding for navigation

Assist in data pipeline activities:

Data collection from robots (logs, sensor data)

Data annotation and preprocessing for model training

Work on feature-level intelligence:

Cleaning optimization behaviours (coverage, path efficiency)

Basic adaptive behaviours based on sensor inputs

Collaborate with ML engineers to:

Validate models in real-world robotic environments

Debug model failures in production scenarios

Use GenAI tools (Copilot, Claude, etc.) to:

Accelerate implementation of ML pipelines and test harnesses

Improve code quality and documentation for AI components

About You

2+ years in robotics or embedded software development

Strong programming skills in C++ (modern standards), Python

Experience in:

Robotics behaviour development (navigation, path planning, control)

Embedded systems and real-time software

Familiarity with software design patterns and clean architecture

Foundational understanding of machine learning principles:

Supervised learning, classification, regression

Basic neural networks and model evaluation concepts

Exposure to robotics perception fundamentals:

Computer vision (e.g., OpenCV, image processing)

Sensor data handling (camera, LiDAR, IMU)

Familiarity with ML frameworks (e.g., PyTorch, TensorFlow Lite) for basic model integration

Understanding of edge/embedded ML constraints:

Latency, memory, compute, and power trade-offs

Experience supporting data pipelines:

Data collection, preprocessing, and labeling workflows

Basic knowledge of robotics behaviour systems:

Navigation, obstacle avoidance, simple planning logic

Awareness of performance optimization techniques:

Multithreading, concurrency, and efficient resource use

Practical experience using GenAI tools (e.g., GitHub Copilot, Anthropic Claude):

Code generation, debugging assistance, and documentation

Strong analytical skills with ability to debug real-world robotics + ML issues

Strong problem-solving mindset and learning agility