Requirements:

• Bachelor’s degree or equivalent practical experience.
• 2 years of experience with software development in one or more programming languages such as C++, or 1 year of experience with an advanced degree.
• 1 year of experience with ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging).
• Experience with on-device ML SDKs/tooling, e.g., MediaPipe, TensorFlow Lite, ExecuTorch, Core ML, SNPE/QNN.

Nice to haves:

• Master's degree or PhD in Computer Science or related technical fields.
• Passion for innovation and a strong desire to push the boundaries of what's possible with on-device ML.
• Excellent communication and collaboration skills.
• Proven track record of leading and delivering successful AI/ML projects focused on on-device deployment (Android, iOS, web browsers, or embedded devices).

What You'll Be Doing:

• Produce multi-task generative models directly on-device to power real-time, low-latency image editing features.
• Develop clean, reusable, cross-platform C++ APIs and native wrappers (Android and iOS) to enable frictionless integration of ML experiences into major partner apps like Google Photos, Snapseed, and YouTube.
• Integrate and deploy multimodal on-device models (such as Gemma) to enable private, local intelligence across text, audio, image, and video natively on-device.
• Optimize and port advanced goal-segmentation models onto edge devices, transitioning server-side prototypes into highly efficient mobile GPU/TPU pipelines targeting real-time tracking.
• Design and build low-latency, on-device audio and speech pipelines (such as direct translation) by developing highly optimized C++ code and MediaPipe graphs.

Perks and Benefits:

Germany: €106000 - €108000 (EUR) + 15% bonus target + equity + benefits