Embedded AI Firmware Engineer for Low-Power Edge ML

Sonova Gruppe

Stäfa

Hybrid

CHF 110,000 - 180,000

Full time

7 days ago

Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Flexible hybrid working model

Training opportunities and growth

Equal opportunity employer

Job summary

Sonova is seeking a Software Engineer Embedded AI to bridge AI and ultra-low-power embedded systems. You will develop the embedded AI software stack for next‑generation hearing instruments and collaborate with AI and DSP experts to deploy DNNs.

You will tailor algorithms to hardware constraints, bring prototypes to production, and maintain code quality through reviews, testing and documentation. A hybrid work setup and development opportunities are offered.

Qualifications

Degree in Computer Science, Electrical Engineering, or a related technical field.
Strong hands-on experience with embedded C++ and Python.
Experience deploying neural networks on embedded systems (TensorFlow Lite, ONNX, TVM, ExecuTorch).
Knowledge of embedded compilers, micro-NPUs and system-level simulation.
Nice to have CUDA and audio/DSP knowledge.
Fluent English with strong written and verbal skills.

Responsibilities

Develop firmware for a deeply embedded AI platform under strict constraints.
Design, implement, and maintain the embedded AI software stack for performance and energy efficiency.
Collaborate with AI and DSP experts to deploy DNNs in hearing-device applications.
Tailor AI algorithms to the platform constraints (quantization, memory, compute, power).
Bring prototypes to production-ready features and integrate with other teams.
Ensure high software quality through clean-code, reviews, testing, and documentation.
Continuously improve ML/DNN development tools, patterns, and practices.