Staff Research Scientist- Speech


Bangalore, IN
  • Job Type: Full-Time
  • Function: Data Science
  • Post Date: 06/09/2021
  • Website:
  • Company Address: Tower D, 9th Floor, IBC Knowledge Park, Bannerghatta Road, Bangalore – 560029, India

About Swiggy

Swiggy went from just 2 neighbourhoods in Bangalore in 2014 to become India’s largest on-demand delivery platform! We have made our mark in 500+ cities and our fleet of Delivery Partners has reached a staggering 2.25 lakh+ individuals, who are hard at work to offer unparalleled convenience for our consumers.

Job Description

About the Team

The Applied Research (AR) team at Swiggy focuses on longterm projects around Computer Vision (CV), Natural Language Processing (NLP) and Speech Technology. We are a bunch of experienced researchers with an aptitude to solve challenging real-world problems in these areas.


Role: Staff Research Scientist in Speech Technology

The AR team at Swiggy is looking for experienced researchers with an aptitude to solve challenging real world problems in the area of Speech Technology. We are looking for a Subject Matter Expert in Speech Technology (Automatic Speech/Speaker Recognition, Speaker Diarization, Text-to-Speech etc), who would be working on some of the important problem statements we are trying to solve: Automatic speech recognition (ASR) for applications like call log analysis and voicebot for English, major Indian languages and mixed languages (words from English and/or Indian language(s) spoken in the same sentence), keyword spotting, biometric authentication using voice, intent classification, sentiment analysis, categorization of output text etc.

What we look for?

  • The potential candidates need to be well versed in classical speech processing methodologies like hidden Markov models (HMMs), Gaussian mixture models (GMMs), Artificial neural networks (ANNs), Language modelling etc.

  • Good understanding of usual machine learning (ML) tools is very important.

  • Hands-on experience of current deep learning (DL) techniques like convolutional neural networks (CNNs), recurrent neural networks (RNNs), long-term short-term memory (LSTM), connectionist temporal classification (CTC) etc used for speech processing is essential.

  • Hands-on coding experience in ML friendly languages like python and knowledge of open source ML/DL libraries like TensorFlow, Keras, PyTorch etc is needed in order to implement the ideas into working proof-of- concepts (PoCs).

  • Experience of working with ASR systems like HTK, Kaldi, DeepSpeech or similar is extremely desirable.

  • The right candidate will have a Masters (M.S./M.Tech. etc) or/and PhD degrees with research experience of 10+/6+ years in speech or related field with an aptitude for research.

  • Preferably should have published their research in conferences and journals of repute.

Related Jobs

Director - Search & Personalization

Swiggy - Bangalore, IN

Product Manager II

Swiggy - Bangalore, IN

Product Manager I

Swiggy - Bangalore, IN

Software Development Engineer in Test

Swiggy - Bangalore, IN

Principal Software Engineer - Backend

Swiggy - Bangalore, IN
Disclaimer: Local Candidates Only
This company does NOT accept candidates from outside recruiting firms. Agency contacts are not welcome.