Senior Research Engineer to improve acoustic modeling and voice biometrics technologies at Spitch

  • The company:

Spitch AG (www.spitch.ch) is an international company focused on speech technologies based in Zurich, with offices in London, Moscow, Madrid, and Milan. The current position is for the Zurich headquarters.

  • Job brief:

We are looking for a Senior Research Engineer to improve our acoustic modeling and voice biometrics technologies. You will be an active member of the core R&D team and will help to develop training recipes, optimize the related existing processes and tools, and bring new technologies to the company.

Your responsibility within the team will increase gradually: you will begin with understanding the basic technology of the company and using it to generate acoustic and speaker verification models for internal projects, and, after some adaptation time, you will work on our core technology to keep it at the state-of-the-art level.

In this role, you should be able to work independently and also to discuss problems and solutions with the rest of the team. You should have excellent organization and problem-solving skills.

  • Responsibilities:
    • Acoustic modeling / speaker verification tools improvement and training recipes enhancement
    • Training and testing models for the company final products
    • Researching the latest modeling techniques
    • Cooperating in customer projects
    • Documenting all remarkable experiments
    • Interpreting data and analyzing results using statistical techniques
    • Providing technical guidance to move research prototypes to production system
  • Required Skills:
    • Graduate degree (Masters or PhD) in Computer Science, Electrical Engineering, Applied Mathematics or equivalent preferred
    • Strong background in Digital Signal Processing and neural networks
    • Solid programming skills
    • 2+ years experience in Python / Perl
    • Knowledge of C/C++
    • Extensive experience in Linux environments
    • Business level proficiency in English
    • Ability to follow existing workflow
  • Desired Skills:
    • Proven working experience in software development
    • 2+ years experience in speaker recognition
    • 2+ years experience in acoustic modeling for speech recognition
    • Experience with open source projects
  • Contract details:

This is a permanent position, with a desired start date in November.

  • Contact:

If you are interested in this offer and believe you are a good match, please send us a copy of your updated CV to hr@spitch.ch