SUMMARY:
For over 25 years, Sensory has developed innovative approaches to embedded (on-device) speech recognition. With our technologies in over 3 billion products, we are always striving to keep our technology
state of the art and make wake-word detection as efficient, accurate, and robust as possible. Our team is seeking an organized, self-motivated, detail-oriented individual to implement, maintain, productize, and otherwise develop our core wake-word recognition technology. A good candidate will be someone with a strong background in software development, speech recognition systems, and machine learning, as well as a collaborative approach to developing new systems and technologies. As a research technologist on our team, you will have the opportunity to address real-world issues in speech recognition technology and recognizer development.
DUTIES AND RESPONSIBILITIES:
- Develop and maintain (including implementing, productizing, and improving) development tools and processes, and speech processing algorithms.
- Implement, support, and productize a variety of machine learning algorithms.
- Research open source methods and implementations and use when applicable.
- Facilitate collaboration and technology transfer across multiple functional groups.
- Work closely with other speech technologists in development of new technologies.
- Work with internal stakeholders to optimize processes and align teams.
- Promote the design and adoption of process best practices, testing, and QA.
PRIMARY SKILLS / SPECIALITY / TECHNICAL SKILLS:
- Programming skills in the development and maintenance of complex software systems.
- A background in signal processing.
- Excellent written and oral communication skills.
- Ability to own and drive multiple high-impact projects simultaneously.
- Self-starter with demonstrated ability to identify and solve new challenges.
Requirements:
- A demonstrated ability with speech recognition concepts and implementing technical solutions
- 5+ years experience developing, testing, and refining algorithms
- 5+ years experience programming in a C-style language and an interpreted language
- Excellent communication and organizational skills.
Preferences:
- Experience working in a collaborative development environment
- Industry experience
- Experience with Unix systems
QUALIFICATIONS:
- MS or Ph.D. in computer science, engineering, mathematics, machine learning, or related field.
- A demonstrated ability to apply speech recognition technologies to real-world applications.
- Experience developing, testing, and refining algorithms.