Verint Systems, Inc. Principal Engineer, Machine Learning in Des Moines, Iowa
Principal Engineer, Machine Learning
Location US-Remote (United States)
Job ID 15704
Overview of Job Function:
The Principal Machine Learning Engineer for Speech Recognition is responsible for developing and improving speech recognition, machine learning, and natural language understanding (NLU) technologies and systems used in a variety of solutions. Solutions include speech and NLU enabled interactive voice response (IVR) telephony applications and various chatbot or conversational-AI solutions.
The Principal Engineer will oversee and perform the development, analysis, and tuning of language models used for speech recognition and machine learning and NLU models used for intent identification and semantic understanding. The role will also develop and tune recognizer grammars used in IVR applications.
The role will work with software engineering teams to guide the development of tools used for model building and management of corpus data. The role will also guide application development teams on how to best leverage speech recognition, machine learning and NLU technologies in applications. The Principal Engineer must be a subject matter expert for issues relating to speech recognition and NLU for application and R&D development teams.
As a key member of a cross-functional team, the Principal Engineer will monitor, analyze, and tune speech and NLU applications to improve performance in:
•Application Effectiveness (how well is the application performing against the business objectives, for example, maximizing call-completion-rate)
•Caller Experience (how good is the overall caller’s experience in using the application)
•Speech Recognition Accuracy (how well does the application understand what the callers are saying)
The Principal Machine Learning Engineer for Speech Recognition will define the future speech recognition and machine learning technologies used in IVR and conversational-AI solutions. They are expected to have knowledge of current and future developments in the industry and guide our technology and software development teams to continue to modernize and improve our speech recognition, machine learning and NLU solutions.
Principal Duties and Essential Responsibilities:
•Develop, analyze and tune language models for speech recognition to be used for both speech-to-text transcription and speech driven natural language understanding (NLU) applications.
•Develop, train, and tune machine learning models for natural language understanding (NLU) and the identification of user intent in conversational-AI solutions.
•Develop, analyze and tune grammars used for speech recognition in IVR applications.
•Improve and optimize the toolchain used for model building and model tuning for speech recognition, machine learning and NLU applications.
•Guide software engineering teams developing toolchain and corpus data systems on best practices and requirements for model building and machine learning.
•Guide software engineering and application development teams using speech recognition, machine learning, and NLU technologies.
•Serve as a subject matter expert for issues relating to speech recognition, machine learning, and NLU for application and R&D software development teams.
•Bachelor’s degree in Engineering, Computer Science or related technical field required, or equivalent work experience
•Minimum of 10 years’ overall experience in an engineering capacity
•Advanced experience working with speech recognition, machine learning and NLU
•Experience with one or more of the following:
o Developing speech recognition (Speech to Text, SST, ASR) systems or solutions.
o Developing and tuning speech recognizer language models for transcription or speech dialog systems
o Building NLU solutions for IVR speech applications such as Nuance Statistical language models (SLM) and Statistical semantic models (SSM).
•Successful completion of a background screening process including, but not limited to, employment verifications, criminal search, OFAC, SS Verification, as well as credit and drug screening, where applicable and in accordance with federal and local regulations
•Master’s Degree or PhD in Engineering or Computer Science
•Experience developing speech recognition systems using open source toolkits like: Kaldi, CMU Sphinx, Pytorch-Kaldi, etc. and/or experience using commercial speech recognition technology like: Nuance, Google, Amazon, etc.
•Experience with language modeling toolkits used for speech recognizers such as Kaldi, HTK, CMU Sphinx, or similar
•Experience building NLU IVR solutions using Nuance or similar speech recognizers
•Experience with natural language dialog systems or voice user interface design
•Experience building conversational AI systems using machine learning or NLU technologies such as Amazon Lex, IBM Watson, Google Dialogflow, Microsoft Luis or similar
As an equal opportunity employer, Verint Systems Inc. prides itself in providing employees with a work environment in which all individuals are treated with respect and dignity. This means we are committed to providing equal opportunity to all qualified employees and applicants for employment without regard to one’s race, color, religion, national origin, age, gender, disability, alienage or citizenship status, marital status, creed, genetic predisposition or carrier status, sexual orientation, Veteran status or any other classification protected by applicable federal, state or local laws. This policy applies to all terms and conditions of employment including but not limited to hiring, placement, promotion, compensation, training, leave of absence or termination.
Verint Systems, Inc.
- Verint Systems, Inc. Jobs