Presto is a market leader in restaurant labor productivity, overlaying next-generation digital solutions onto the physical world. Its enterprise-grade touch, vision, and voice technologies help hospitality businesses thrive while delighting guests. Presto’s solutions are designed to enable restaurants to do more with less by increasing their guest-to-staff ratios, improving speed and quality of service, identifying bottlenecks, and offering guests a superior experience. These solutions include:
- Voice: Guests and staff can place orders in a natural conversational style via automated speech recognition with over 94% accuracy, even in noisy environments.
- Vision: Using just a few cameras, restaurants can measure throughput and order accuracy, identify issues, and implement real-time solutions.
- Touch: Custom designed for both drive-thru and dine-in applications, the same tablet can be deployed as a pay-at-table, staff handheld, kiosk, or drive-thru line buster—offering wide front-of-house flexibility.
We are looking for a principal or senior engineer to develop state-of-art speech recognition tech and integrate the latest results into existing and future voice products. In addition, the qualified candidate should also actively search for new ASR tech and support the definition of Presto’s new voice features and voice product roadmap for our customers so as to continuously improve user satisfaction and workforce productivity.
Responsibilities
- Drive the development and customization of state-of-art high-performance ASR engines for Presto business customers
- Support the integration and optimization of ASR engines into voice products
- Together with other team members to define required speech data for new voice product features.
- Communicate with product and sales teams about tech performance and limitations and provide recommendations for use cases
- Mentor junior members in the speech team
Qualifications
- Master’s degree in computer science or electrical engineering.
- At least 10 years of experience in the speech recognition field
- Deep understanding and hands-on development of state-of-art automatic speech recognition systems
- Hands-on development experience and knowledge in state-of-art traditional machine learning and deep learning algorithms
- Hands-on working experience with real-time speech systems and able to integrate the latest development quickly
- Strong programming skills in Python, C, or C++
- Good knowledge about embedded speech recognition systems
Nice to have
- PhD in computer science or electrical engineering
- Hands-on experience in using and fine-tuning near and far-field speech signal processing algorithms
- Hands-on experience in using and fine-tuning text to speech algorithms