Senior Machine Learning Engineer (Audio)

Xperi invents, develops and delivers technologies that enable extraordinary experiences. We make entertainment more entertaining, and smart devices smarter.

From the home to the car to everywhere in between, managing content and connections in a way that is smart, immersive, and personal is precisely what Xperi’s technologies do.

Our inventions are foundational to the global entertainment ecosystem and our products and data improve every aspect of the digital entertainment experience, from choice to consumption.

In this role you will  working on the development of  leading edge ML technologies running on advanced edge AI devices.

You will

• Fulfill a technical leadership role in a team working on cutting-edge AI and ML research and application development
• Develop innovative ML and Deep learning algorithms for Audio and Multimedia applications running on advanced edge AI SOCs.  
• Work with business stakeholders to drive application development from initial concept to implementation , and align the technical goals to the overall product Roadmap.
• Apply ML to real-world problems selecting, designing, optimizing, and deploying neural networks across a wide range of Audio and Multimedia use cases
• Work with Data teams to establish the training and testing datasets.
• Generate technical documentation.
• Keep up to date with latest advances in machine/deep learning, both industry and academia
• Develop and submit invention disclosures
• Demonstrate a structured and detail-oriented approach and follow rigorous scientific and engineering methods

Requirements

• Minimum 4-5 years of industry experience in the development and productisation of AI/ML technologies for Audio & Multimedia applications.
• Strong experience with applying ML & Deep learning to Audio & Multimedia.
• Good knowledge of Digital Signal Processing for Audio.
• Experience with speech recognition, voice recognition, acoustic event detection, voice biometrics 
• A proven track record of conducting disciplined and productive R&D
• MSc degree in a relevant field
• Familiarity with optimising and deploying ML / Deep learning technologies on embedded ML accelerators
• Familiarity with state-of-the-art ML, conversant in the latest ML developments, neural network architectures, and training and optimization methods
• Proficiency with deep learning development tools such as PyTorch, TensorFlow, Caffe
• Solid Python and C/C++ programming language skills
• Strong analytical and troubleshooting skills
• Excellent written and spoken communication skills
• A strong drive to solve problems and disrupt the status quo
• Familiarity with version control systems, preferably Git and development methodologies such as Agile/Kanban
• Highly desirable
• PhD in a related field
• Advanced knowledge and expertise in: machine learning, neural networks, information theory, statistics and probability, modelling and optimization
• Demonstrated interest in audio and imaging: acquisition, processing, analytics and display, IoT, AR/VR/MR, autonomous driving