656 geprüfte KI-Jobs

Aufgaben

As an Edge AI ML Engineer, you will develop, optimize, and deploy machine learning models for audio and multimodal intelligence on real devices. You will work at the boundary of ML modeling, DSP, and embedded systems, turning research concepts into efficient, robust, production-ready algorithms. You will collaborate closely with ML researchers, DSP experts, firmware engineers, and hardware teams to design algorithms that perform well not only in the lab, but also under real-world constraints such as latency, memory and power.

This role is ideal for an ML engineer who enjoys model development, experimentation, and algorithm design, while also caring deeply about whether those models can run efficiently on edge hardware. In This Role, You Will Identify opportunities for new DSP/ML algorithms by deeply understanding device constraints, sensor characteristics and hardware capabilities (MCU, DSP, NPU). Develop audio and multimodal ML models for embedded and edge AI applications.

Design, train, evaluate, and iterate on models for real-world sensing and interaction use cases. Prototype novel approaches that push what’s possible in lowlatency, ondevic audio and multimodal processing. Embedded / OnDevice Engineering Develop software for RTOS environments (e.g., FreeRTOS) and deploy models to device runtimes and hardware accelerators (DSP, NPU, MCU).

Convert trained ML models into efficient embedded implementations (C/C++, quantization, fixedpoint inference). Optimize runtime performance: memory footprint, SRAM usage, latency, and power consumption. Integrate ML inference into realtime firmware pipelines.

Design endtoend embedded AI systems (sensor → preprocessing → model → postprocessing). Platform & Performance Engineering Architect reusable embedded ML platform components usable across multiple hardware targets. Profile and optimize performance on MCUs, DSP cores, NPUs, and custom accelerators.

Work with crosscompilation toolchains, CMakebased builds, and modular codebases. Integrate with ondevice ML runtimes (e.g., TFLite Micro, ExecuTorch, custom interpreters). Provide actionable feedback on model architecture for deployment efficiency and realtime behavior.

Required Qualifications Strong proficiency in C/C++ for embedded systems. Strong experience developing and evaluating machine learning models, preferably for audio, speech, or other time-series sensor data. Experience optimizing ML models for edge, embedded, or resource-constrained environments.

Proficiency in Python for model development, experimentation, evaluation, and tooling. Preferred Qualifications Master’s or Ph.D. in Computer Science, Electrical Engineering, Machine Learning or related field. Experience with ML compilers/frameworks such as MLIR, Glow, ExecuTorch.

Experience with real-time streaming inference pipelines. Knowledge of acoustics and classical audio DSP. Experience with on-device ML (TinyML, quantization, pruning).

Publication track record in ML, DSP, systems, or embedded AI. You Might Thrive Here If You… Love building systems where algorithms meet real hardware. Enjoy profiling and optimizing code under tight compute and memory constraints.

Take ownership — from prototype to hardware bringup to production. Want your work to directly shape the next generation of audiodriven experiences.

Zur Position

StreamUnlimited is a passionate team of 120 music lovers and tech geeks across Vienna (HQ), Bratislava, Boston, Shenzhen, and Osaka, on a mission to make the global home streaming experience downright awesome. For over 20 years, we have delivered what we promise because we genuinely care about our people and our work. Following our acquisition by Bose in 2026, we are now empowered to do even more of what we love.

We are building the algorithms, systems, and platforms that power the next generation of audio and multimodal experiences—from embedded devices to cloudconnected products. Our ambition is bold: to become the world’s Audio Lab — inventing, optimizing, and delivering meaningful and magical experiences anywhere sound matters. We sit at the intersection of digital signal processing (DSP), deep learning, embedded systems, and software infrastructure, turning new ideas into realworld capabilities across a wide range of hardware and product surfaces.

Our group: Invents and develops audio and multimodal ML algorithms for real-world product experiences. Designs efficient neural networks and signal processing pipelines for embedded and on-device deployment. Optimizes models for resource-constrained hardware, including MCUs, DSPs, NPUs, and custom accelerators.

Build tools, infrastructure, and reference implementations that accelerate the journey from invention prototype product. Learns from real-world deployment constraints to inform the next generation of algorithms, models, and platforms. If you love building ML systems where algorithms meet real hardware –– and you want your models to run efficiently in the real world –– this is the place.

About