Research Assistant in Embedded AI (all genders) - Speech and Audio Applications

Fraunhofer Institute for Integrated Circuits IIS; Erlangen; On-site; EUR 65,000 - 90,000; Full time

Benefits offered by this job

An exciting role: diverse,国际es Umfeld,

Room for creativity: Pragmatische Um‑/

Job summary

Fraunhofer IIS in Erlangen sucht eine/n Forscher/in/Engineer im Bereich Audio und Media Technologies. Sie entwickeln Lösungen zur Bereitstellung und Integration von ML-Modellen für mobile und Embedded-Geräte, um Echtzeit-Ausführung zu ermöglichen.

Sie optimieren Algorithmen unter Speicher- und Rechen-Einschränkungen, prüfen Algorithmenverhalten im Audiobereich und sichern hochwertige Software durch Tests, sauberen Code und Audiosystem-Expertenwissen. Teilzeit/Hybrid, 39 Stunden.

Qualifications

• Master’s, Ph.D. or equivalent in Electrical Engineering, Computer Science, or a related field.
• Strong programming skills in C/C++ and Python, with experience in deep learning frameworks (PyTorch, TensorFlow).
• Solid Linux experience, including shell scripting and build tools (gcc, make, cmake).
• Practical knowledge of DNN runtimes (ONNX, TensorFlow Lite) and optimization techniques (pruning, quantization).
• Experience with audio DSPs, hardware SDK configuration, or DSP for speech and audio is a plus.
• Fluent English and ability to work in international, multidisciplinary teams.
• Strong analytical and problem-solving skills with a structured approach to debugging.

Responsibilities

• Develop solutions to deploy and integrate machine learning models across platforms for real-time execution on mobile and embedded devices.
• Adapt algorithms to constraints on memory and compute while maintaining high performance.
• Apply signal processing expertise to test, validate, and verify algorithmic behavior in audio processing scenarios.
• Maintain high software quality through clean code, automated testing, and robust audio processing systems.

Skills

C/C++ programming

Python programming

Deep learning frameworks

Linux environments

Shell scripting

Build tools (gcc, make, cmake)

DNN runtimes (ONNX, TensorFlow Lite)

Model compression & quantization

Audio DSPs / Speech processing

English language

Multidisciplinary teamwork

Education

Master’s, Ph.D. or equivalent in Electrical Engineering, Computer Science, or related field

Tools

GCC

Make

CMake

ONNX

TensorFlow Lite

Job description

Welcome to the Fraunhofer Institute for Integrated Circuits IIS

As the largest institute within the Fraunhofer-Gesellschaft, we have been conducting research for over 30 years in diverse fields such as artificial intelligence, microelectronics, sensor systems, data acquisition, signal processing, and signal transmission. Talented individuals from various engineering and natural science disciplines will find a wide range of exciting research topics under one roof. A few highlights that reflect our innovative strength include neuromorphic computing, 5G/6G mobile communication technologies, generative AI in speech and signal processing, and X-ray imaging for e-mobility. And that’s just the beginning! What sustainable solution will you find with us?

Be part of change

The division »Audio and Media Technologies« is one of the world’s leading organizations in audio, speech, and media processing. For over 25 years, it has been shaping innovations in sound and vision – including groundbreaking technologies such as mp3 and AAC codecs. More than 200 engineers and scientists develop cutting‑edge solutions that are used worldwide.

• Bring research into real‑world applications: You develop solutions for efficiently deploying and integrating machine learning models across platforms, enabling efficient real‑time execution on mobile and embedded devices.
• Optimize for performance and efficiency: You adapt algorithms to meet strict constraints on memory consumption and computational complexity while maintaining high performance.
• Ensure correctness through strong fundamentals: You apply your expertise in signal processing to test, validate, and verify algorithmic behavior in practical audio processing scenarios.
• Maintain high software quality standards: You implement clean, reliable code and ensure robustness through automated testing, quality assurance practices, and solid experience with audio processing systems.

What you contribute

• Master’s, Ph.D. or equivalent in Electrical Engineering, Computer Science, or a related field.
• Strong programming skills in C/C++ as well as good knowledge of Python, including experience with deep learning frameworks (e.g., PyTorch, TensorFlow).
• Solid experience with Linux environments, including shell scripting and build tools (e.g., gcc, make, cmake).
• Practical knowledge of DNN runtimes (e.g., ONNX, TensorFlow Lite) and optimization techniques such as model compression and quantization (e.g., pruning, quantization-aware training).
• Experience with audio DSPs, hardware SDK configuration, or digital signal processing for speech and audio is a plus.
• Fluent English and ability to work effectively in international, multidisciplinary teams.
• Strong analytical and problem‑solving skills with a structured, root‑cause‑oriented approach to debugging.

What we offer

• An exciting role: We offer a diverse and challenging field of work in an international environment, oriented toward state‑of‑the‑art research and technology.
• Room for creativity: Projects with strong practical components motivate our employees to drive innovation.
• Our colleagues enjoy our positive work culture: We are open‑minded, we help and trust each other.
• Top of the line infrastructure at your workplace: With our state‑of‑the‑art technologies, we develop solutions to meet the challenges of today and tomorrow.
• We value personal contact: With our structured onboarding process, you will quickly become familiar with our institute and be able to extend your network successfully.
• We take your needs seriously: We support your work‑life balance by offering flexible working hours and hybrid work.
• Your goals and interests are important to us: We offer ongoing professional and personal seminars, coaching, and language classes.
• We offer complimentary parking spaces, charging stations for electric cars, covered bicycle parking, and showers at the institute.
• In‑house health management, including sports courses, running groups, and relaxation seminars.

The position is initially limited to 2 years with the aim to extend it subsequently. The weekly working time is 39 hours. Attendance in person at the institute is required for 3 days. The position can also be filled on a part‑time basis with a preference, however, to have it filled as close to a full‑time position as possible.

We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Appointment, remuneration and social security benefits based on the public‑sector collective wage agreement (TVöD).

About Fraunhofer

The Fraunhofer-Gesellschaft currently operates 76 institutes and research institutions throughout Germany and is the world’s leading applied research organization. Around 32 000 employees work with an annual research budget of 3.4 billion euros. The Fraunhofer Institute for Integrated Circuits IIS, headquartered in Erlangen, is the largest institute of the Fraunhofer-Gesellschaft with more than 1 200 employees.

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.

Fraunhofer is not only the largest organization for applied research (application‑oriented research organisation) in Europe, but also a top‑rated employer.

Ready for change?

Fraunhofer Institute for Integrated Circuits IIS
www.iis.fraunhofer.de