Software Engineer Embedded AI (m/f/d)

At Sonova R&D, we are not just developing hearing devices, we are shaping the future of hearing technology. At the heart of this transformation is the deployment and execution of neural networks on our next-generation embedded platform. This requires innovative tools and firmware infrastructure, giving you the opportunity to directly influence the performance of our products.

As our new Software Engineer Embedded AI you will bridge the gap between cutting-edge AI and ultra-low-power embedded systems. You will develop the embedded AI software stack that forms the foundation of our next-generation hearing instruments.

Are you excited to explore new technological territory and play a pivotal role in shaping Sonova’s edge AI capabilities? Join us and help rethink how embedded software is built to enhance people’s hearing experience and quality of life.

More about the role

• Develop firmware for a deeply embedded AI platform operating under strict latency, memory, compute, and energy constraints
• Design, implement, and maintain the embedded AI software stack including optimization for performance, latency, and energy efficiency
• Collaborate with AI and DSP experts to analyze and deploy DNN algorithms in hearing-device applications
• Tailor AI algorithms to the embedded platform and its constraints (e.g., quantization, memory, compute and power)
• Implement prototypes, bring them to production-ready features and integrate them into our system in collaboration with other engineering teams.
• Ensure high software quality through clean-code practices, code reviews, testing, documentation, maintenance, and root-cause analysis
• Continuously improve development methodologies, tools, design patterns, and best practices for efficient ML/DNN development and deployment

More about you

• Degree in Computer Science, Electrical Engineering, or a related technical field
• Strong hands-on experience with embedded C++, Python, and object-oriented programming
• Experience developing and deploying neural networks on embedded systems, including familiarity with deployment frameworks such as TensorFlow Lite, ONNX, TVM, or ExecuTorch
• Knowledge of embedded compilers, micro-NPUs, and system-level simulation
• Experience with CUDA is an advantage
• Knowledge of audio or digital signal processing is an advantage
• Experience in bringing features to products is an advantage
• Fluent English, with strong written and verbal communication skills

More about what we offer

As one of the world’s leading hearing care providers headquartered in Switzerland, we’re committed to building an inclusive culture. We want to create an environment where you can balance a successful career with your commitments and interests outside of work, through our flexible hybrid working model. We offer a wide range of training opportunities for both your professional and personal development, and there are exceptional growth opportunities with individual development plans. 

Application process

Magdalena Suszek, Talent Acquisition Partner, is looking forward to receiving your application via our online job application platform, including your CV and cover letter. For this vacancy, only direct applications will be considered.