onsite
Speech Recognition Engineer
Speech Recognition Engineer
The Speech Recognition Engineer will focus on improving speech-to-text pipelines, including transcription and diarization, for Level AI's ASR engine. This role involves training, deploying, and maintaining scalable ASR pipelines while staying updated on state-of-the-art techniques.
About the role
About the Role
As a Speech Recognition Engineer, you will be working on cutting-edge problems within speech-to-text pipelines, contributing to the development and enhancement of Level AI's Automatic Speech Recognition (ASR) engine.
Responsibilities
- Work on problems arising in speech-to-text pipelines, such as transcription, diarization, voice activity detection.
- Train, deploy and maintain scalable automatic speech recognition pipelines to power Level AI’s ASR engine.
- Keep abreast of SOTA techniques in ASR and exchange knowledge with colleagues.
- Work with other team members to develop the architecture & design of systems.
- Ability to independently conduct experiments with model architectures, training schemes, and approaches proposed in ASR literature.
- Work in an agile environment to deliver high-quality products.
Skills
ASRspeech to texttranscriptiondiarizationvoice activity detectionmodel architecturestraining schemesAgile