Research Scientist Intern, Spatial Audio Capture and Reproduction (PhD)

Meta; Redmond (WA); On-site; USD 34,000 - 48,000; Full time

Job summary

Meta Reality Labs Audio internship seeks a PhD candidate to design and implement novel algorithms for spatial audio research, including experimentation and evaluation of new audio technologies. The role involves collaboration with researchers across audio and acoustic disciplines, and communication of research progress.

Applicants should have ML and programming skills, experience with spatial audio, and a track record of publications.

Qualifications

• PhD or in progress in Acoustics, CS, ME, EE or related STEM fields.
• 1+ years experience working with spatial audio capture algorithms.
• Expertise in audio signal processing, binaural audio, microphone array processing, ML for spatial audio, beamforming or spatial audio coding/perception.
• Coding experience in C/C++, C#, Python, Max/MSP, or MATLAB.
• Must have work authorization and experience with real-time multichannel audio processing and ML platforms such as PyTorch/TensorFlow.
• Experience with Unity, Unreal, CryEngine or similar game engines.
• Proven publications in top conferences/journals (ICASSP, WASPAA, Interspeech, JASA, JAES).
• Ability to work cross-functionally in a team and communicate results.
• Intent to return to a degree-program after internship.

Responsibilities

• Design and implementation of novel algorithms to solve audio research problems.
• Experimental design, implementation, and evaluation of new audio technologies.
• Collaborate with researchers across audio and acoustic engineering disciplines.
• Communicate research agenda, progress, and results.

Skills

Spatial audio

Machine learning

Real-time audio

Cross-functional teamwork

Education

PhD in Acoustics/CS/ME/EE

Tools

PyTorch

TensorFlow

Unity

Unreal Engine

CryEngine

Max/MSP

MATLAB

Job description

About

The Meta Reality Labs Research Team brings together a world-class team of researchers, developers, and engineers to create the future of virtual and augmented reality, which together will become as universal and essential as smartphones and personal computers are today. And just as personal computers have done over the past 45 years, AR, VR and MR will ultimately change everything about how we work, play, and connect. We are developing all the technologies needed to enable breakthrough AR glasses and VR headsets, including optics and displays, computer vision, audio, graphics, brain-computer interfaces, haptic interaction, eye/hand/face/body tracking, perception science, and true telepresence. Some of those will advance much faster than others, but they all need to happen to enable AR, VR and MR that are so compelling that they become an integral part of our lives.In particular, the Meta Reality Labs Research audio team is focused on two goals; creating virtual sounds that are perceptibly indistinguishable from reality and redefining human hearing. See more about our work here: https://tech.facebook.com/reality-labs/. These two initiatives will allow us to connect people by allowing them to feel together despite being physically apart and allow them to converse in even the most difficult listening environments. The Augmented Capture research team of the Meta Reality Labs Audio is seeking interns to help us create unique audio experiences for virtually reliving and sharing real life experiences using spatial audio capture.Specific projects will be designed in collaboration with successful applicants to align the intern’s skills and experience with current research needs.Our internships are twelve (12) to twenty-four (24) weeks long and we have various start dates throughout the year.

Responsibilities

• Design and implementation of novel algorithms to solve audio research problems.
• Experimental design, implementation, and execution to evaluate new audio technologies.
• Collaboration with and support of other researchers across audio and acoustic engineering disciplines.
• Communication of research agenda, progress, and results.

Minimum Qualifications

• Currently has, or is in the process of obtaining, a PhD degree in the field of Acoustics, Computer Science, Mechanical Engineering, Electrical Engineering or related STEM fields
• 1+ years experience working with spatial audio capture algorithms
• Expertise in one or more of the below research areas: Audio signal processing, Binaural audio technology, Microphone array processing, Machine learning for spatial audio applications, Beamforming, Spatial audio evaluation, Spatial audio coding, Spatial audio perception
• Coding experience in one or more languages, including but not limited to: C/C++, C#, Python, Max/MSP, or MATLAB
• Must obtain work authorization in the country of employment at the time of hire and maintain ongoing work authorization during employment Experience with real-time multichannel audio processing and coding
• Experience with machine learning software platforms such as PyTorch, TensorFlow, etc
• Experience with Unity, Unreal, CryEngine, or similar game engines
• Proven track record of achieving results as demonstrated in accepted papers in top conferences or journals such as ICASSP, WASPAA, InterSpeech, JASA, JAES, etc
• Experience working and communicating cross functionally in a team environment
• Intent to return to a degree-program after the completion of the internship/co-op