Speech Recognition Engineer

AISense's main product is Otter: a smart, note-taking and collaboration app that empowers you to remember, search, and share your voice conversations. Try it now on http://otter.ai, Otter - Appstore, and Otter - Google Play.

With Otter, we are adding new life to conversations of all types. Our Ambient Voice Intelligence™ technology processes verbal conversations to derive usable text and identify speakers. It is integrated with a variety of applications. Our direct-to-end user product will change meetings by generating interactive notes that are saved in one place and ready for sharing. Leading unified communications and online collaboration providers partner with AISense to offer transcription, deep content search, summarization, and conversational analytics.

We are seeking an experienced Speech Recognition Engineer to help lead the development and deployment of new AI technology to solve challenging technical problems in processing collaborative voice conversations to join our technology team. Members of the technology team work collaboratively as a group and with colleagues in engineering and product to devise and deploy new technologies for speech recognition, speaker separation, diarization, and speaker identification.

You will:

  • Participate in the whole scope of our application development where you will be working closely with our team in the design and implementation of algorithms, tools and methodologies in speech research, voice interface design, application prototyping, and development of our proprietary speech recognition engine
  • Take part in extending and improving components of our speech understanding platform

To be a successful candidate, you must have:

  • BS in CS or EECS
  • A very strong machine learning background with deep structured learning/hierarchical learning and statistical modeling techniques that can be applied to speech 
  • Strong software engineering skills in one or more of the following: Java, Python, and C++
  • Solid experience with building automatic speech recognition systems that can be integrated in an information retrieval process  
  • Solid experience with Kaldi
  • Curiosity to seek and understand causes of error in AI models and proven ability to propose novel and creative solutions
  • Comfort in being part of a highly collaborative start up environment with a tight team where you will be  involved in all aspects of the development: building infrastructure, data capture, and model training

Nice to Have:

  • Master's or PhD in relevant discipline is highly desirable, but others with strong academic backgrounds and equivalent experience are encouraged to apply

**Please note: AISense does not accept unsolicited resumes from 3rd party recruitment agencies without a written agreement in place for permanent placements. Any resume or other candidate information submitted outside of established candidate submission guidelines (including through our website or via email to any AISense employee) and without a written agreement otherwise will be deemed to be our sole property, and no fee will be paid should we hire the candidate.

Want to apply later?

Type your email address below to receive a reminder

ErrorRequired field

Apply to Job

ErrorRequired field
ErrorRequired field
ErrorRequired field