Staff Software Engineer, Voice Experience Job in Vocera Communications.

Position Description: Vocera is looking for a hardworking, hands-on Staff Software Engineer, Voice to join our dynamic and growing organization. You will be responsible for the design and implementation of the Vocera Voice technologies and infrastructure. In this role you will own specific research areas that can translate into solutions that provide intuitive voice experience in a clinical setting and develop speech and NLP engines using public cloud tools. This position reports to the VP, Strategic Technology Acceleration.

Responsibilities

• Partner with Voice Experience research team to develop deep understanding of open source and commercial speech and NLP engines
• Develop speech models for conversational speech and train them with Open Source datasets as well as Vocera dataset using public cloud environments
• Use Adaptation and other techniques to improve the model
• Develop capabilities to improve recognition capabilities for Names and Commands
• Develop ML based intent engines that can provide high fidelity intent recognition of natural clinical communications
• Develop tools that will measure and analyze the fidelity of speech and intent recognition capabilities
• As a key member of the India development team you will take ownership of the important area of the solution, Voice Experience
• Technically lead engineers in the team to deliver the necessary Voice Experience capabilities as part of the overall platform

Competencies

• Strong Python and C++/Java experience in developing solutions
• Be able to understand latest development on Voice Technologies by reviewing journal articles and translate that into actionable inferences
• Published or Co-authored papers in the Voice Technology areas establishing research credentials
• Strong understanding of open source speech engines like Kaldi or Deep Speech
• Expertise with Python to develop train speech models using various datasets
• Create recipes to develop Vocera specific models for the speech engines
• Strong understanding of Public Cloud APIs like GCP or AWS
• Working experience using Git, Jira, Jenkins in an Agile methodology-based environment
• Driven with the ability to work independently and execute against deadlines
• Ability to work closely with our dynamic multi-functional team across geographies to deliver the solutions
• Ownership Hands on approach to the full product speech, NLU engine life cycle from building, training and enhancing the models to meet Vocera use cases
• Demonstrated passion to build great products
• Resourceful, inventive and able to solve complex problems using online and team resources

Requirements

• MS in Computer Science, PhD in Speech Sciences preferred or related discipline, or equivalent
• 12+ years of C++/Python based development of speech engines or related work
• 5+ years experience using open source engines like Kaldi or DeepSpeech for developing Speech Recognition and Intent Recognition pipelines
• Proven experience on training and augmenting speech models on specific datasets to meet the desired Word Error Rate metrics
• Experience in building speech accent models to handle users with varied accents
• Proven experience developing Python tools for assessment and analysis
• Working with Public cloud technologies like GCP or AWS environments developing models and building voice decoding pipelines
• No travel required