Whisper.ai is building the world’s first noise cancelling hearing aid system: it analyzes your audio in real time, automatically filtering out noise and amplifying the sounds you want to hear. Unlike traditional hearing aids, which simply amplify everything in the room, Whisper amplifies the person you’re listening to based on millions of audio prints it learns over time so it’s able to pick out who you’re listening to, even in the noisiest restaurant.

Based in San Francisco, Whisper is lucky to have the support of great investors including Sequoia Capital, First Round Capital, LUX Ventures, and more.  

THE ROLE

As the Audio DSP Engineer at Whisper, you’ll be responsible for developing new algorithms for a next generation wireless hearing aid platform. This will include developing novel techniques in acoustic modeling as well as tweaking existing algorithms to be best optimized for our hardware platform and consumer use case.

This role will span both algorithms research and prototyping (e.g. MATLAB or Python) as well as writing shipping code on the target hardware (e.g. Assembly and C) to bring these algorithms to customers.

RESPONSIBILITIES

  • Develop new techniques in acoustic modeling optimized for a hearing aid system that includes deep learning audio processing.
  • Optimize existing (either in-house or vendor-provided) algorithms to our hearing aid system.
  • Debug and improve audio processing performance on target hardware using manufacturing samples.
  • Receive feedback from customers improve the hearing experience in the Whisper hearing aid system in conjunction with the machine learning acoustics team.

MINIMUM QUALIFICATIONS

  • Product focused: Excited to work at a young company and take a major role in developing a new hardware product that will help people hear better in everyday situations.
  • 3+ years of industry experience in designing and implementing audio DSP algorithms related to audio and/or speech processing in a hardware product.
  • Strong theoretical background of signal processing techniques including adaptive filtering, filter banks and wavelet processing, speech analysis and synthesis, speech and audio coding.
  • Comfortable prototyping audio algorithms (e.g. MATLAB or Python) and bringing these algorithms to the DSP by writing customer-facing code (e.g. Assembly and C).
  • Understanding of analog and digital audio processing (in particular filter theory and design) and adaptive audio processing algorithms.
  • Experience working in a team software engineering environment (e.g. code reviewing, source control, etc).

BONUS POINTS

  • Familiar with traditional statistical modeling/feature extraction techniques (GMM, HMM, NMF / spectrograms, MFCC etc) for voice recognition and audio event classification.
  • Experience with machine learning techniques (e.g. deep neural nets) to solve audio tasks like audio event classification or voice detection.
  • Electrical (analog and digital) audio design knowledge.
  • Audio qualification experience, including calibration procedures, test procedures, equipment, tools, etc.

If you're interested in difficult and novel problems in embedded audio, immediate ownership of company defining decisions, top compensation, and work which directly helps 360MM+ people hear again - we'd love to hear from you.

Whisper is an equal opportunity employer committed to a diverse workforce with an inclusive working environment for everyone to do their best work. We do not discriminate on the basis of race, ethnicity, religion, gender, gender identity, sexual orientation, age, marital status, veteran status, or disability status. 

Apply for this Job

* Required