Incubator - Blue Canoe: Lead Engineer, Speech Processing & Machine Learning
Blue Canoe Learning is seeking a MS or PhD graduate with experience in Speech Recognition and Machine Learning to join our team.
Over two billion people around the globe are learning English, the operating system of the world’s global business conversation. Unfortunately, mastery remains elusive to hundreds of millions of professionals due to the challenge of pronouncing 14-different critical vowel sounds – the “last mile” of language. Mastery here often makes the different between getting that job interview or promotion, being seen as an outsider in an organization, or being able to build empathy and rapport with customers, patients, or business partners. It is mission-critical for hundreds of millions of jobs.
We are building a suite of tools, starting with a mobile app that engages English learners through a game, played with your fingers and your voice. Our speech recognition technology uses machine learning and Alexa-like coaching to give people a personal pronunciation coach on their phones. We track progress and create custom training programs for each user that adapts to their specific country of origin, as people from China pronounce English words differently than people from Brazil. We also provide the ability to upload different language libraries, as people in the shipping industry will have different jargon than people working in medicine. Moreover, we’re not just talking, we’re doing. We have active pilot programs with some of the biggest companies in the world and we’re growing fast.
We’ve brought together a CEO with six exits, a CTO with 18 years of senior technology leadership at Microsoft, and a world-leading expert in teaching English. Our team also holds a patent for an approach to learning English that uses brain science to solve the key pronunciation problem, a solution endorsed by the U.S. State Department. We are also one of the few companies in the world to be accepted into the new startup incubator at the Paul Allen Institute for Artificial Intelligence. Our team collaborates alongside 75+ AI PhDs and researchers, working to take our speech processing and machine learning technology to the next level. It’s an extraordinary opportunity to push the bleeding edge of what’s possible – and do it for an extraordinarily worthy cause: Helping people communicate.
ABOUT THE ROLE:
We seek a full time MS or PhD graduate with experience in Speech Recognition and Machine Learning to join our team, full-time. In this position, you will lead the design of our architecture, refine our current speech processing solution, and work to deliver solutions that are more and more effective and scale to large numbers of end users all over the world. Our team is small, fun, highly efficient, and results-oriented. We work in an agile and collaborative environment that stays focused on what matters. This position is based in Seattle or Bellevue WA.
- Knowledge of current speech processing/recognition techniques
- Ability to design a flexible pipeline for label collection, feature engineering, training and evaluation of ML models
- Ability to deploy, monitor and tune models
- Ability to iterate quickly and efficiently with a team of linguists, software developers, and designers
- Strong problem solving and troubleshooting skills
- Excellent written and verbal communication skills
- Ability to work independently in a fast-paced environment with frequent production releases
- Legally eligible to work in the U.S. on an ongoing basis