The ideal candidate combines a high level of creativity and analytic ability, with get-it-done practicality and excellent work quality. This individual will be part of the team that creates and deploys to the market best-in-class deep learning-based speech recognition and natural language solutions on smartphones, tablets, PCs, and consumer electronics.
PRIMARY DUTIES AND RESPONSIBILITIES:
- Architects and implements deep learning-based or conventional speech recognition, speech synthesis, and voice processing software on a variety of DSP-based and ARM-based platforms.
- Evaluates new processor platforms for feasibility of implementing Sensory technologies.
- Defines and implements simulations and scripts for validating, evaluating, and improving the performance of Sensory technologies.
- Learns and understands existing proprietary Sensory technology in depth.
- Collaborates with the theoretical algorithms development group in the development and improvement of speech recognition, synthesis, and voice processing algorithms.
- Three or more years of experience in embedded software development.
- Working knowledge of a few commercial DSP-based and/or ARM-based platforms.
- Proficiency in embedded “C”, demonstrated by a past primary programming role in one or more fully-released products.
- Ability to develop software from existing code, detailed specification, or general conceptual outline; equally adept at high-level algorithmic software design and low-level code optimization.
- Good oral and written communication skills, ability to exchange and debate complex technical concepts face-to-face or remotely.
- MS in EE or CS
- Knowledge of digital audio and speech processing
- Experience with Python, Perl, or similar scripting languages
Job code #: 2110-ZC