Voice Recognition Engineer

Title: Voice Recognition Engineer

*Local to MO

Description:

Skills for this job

• design and implement speech-driven interfaces - work seamlessly across major browsers

• alternative speech processing frameworks beyond Web Speech API (e.g., Kaldi, DeepSpeech)

• extending Web Speech APIs and related technologies to deliver accurate, responsive, and user-friendly voice recognition experiences

• improve speech recognition speed, accuracy, and noise resilience

• speech recognition for noisy environments

• multilingual voice recognition and configurable speech duration features

• building accessible and inclusive voice-driven interfaces

• Expertise natural language processing (NLP) or machine learning techniques for speech

We're seeking a Voice Recognition Engineer to design and implement speech-driven interfaces that work seamlessly across major browsers. This role focuses on tailoring and extending Web Speech APIs and related technologies to deliver accurate, responsive, and user-friendly voice recognition experiences. You'll help us unlock natural voice interaction for our products, ensuring accessibility, speed, and reliability across platforms. Will be contract only, starting out as 6 months could be longer,

The Voice Recognition Engineer will design and optimize browser-based speech interfaces, focusing on cross-browser compatibility and accuracy. They will collaborate with product teams to enhance accessibility and user experience, leveraging and extending Web Speech APIs to deliver reliable voice interactions across platforms.

1. Required Skills and Experience

Experience applying voice recognition technologies across multiple browsers (Chrome, Edge, Safari, Firefox, and others)

Proficiency in tailoring and customizing Web Speech API and related frameworks

Demonstrated ability to improve speech recognition speed, accuracy, and noise resilience

Strong understanding of cross-device compatibility for desktops, laptops, tablets, and smartphones

Collaborative experience working with product, design, and technical teams to integrate voice features

Proven track record in optimizing speech recognition for real-world, noisy environments

Ability to support multilingual voice recognition and configurable speech duration features

1. Desired Skills and Experience

Knowledge of alternative speech processing frameworks beyond Web Speech API (e.g., Kaldi, DeepSpeech)

Experience in building accessible and inclusive voice-driven interfaces

Familiarity with performance benchmarking and model refinement for voice recognition

Certifications or training in speech recognition, AI, or related fields

Domain expertise in natural language processing (NLP) or machine learning techniques for speech

1. Preferred Qualifications

Demonstrated adaptability to various collaboration environments and Agile workflows

Passion for innovation in voice interaction technologies

Strong problem-solving and troubleshooting skills in browser compatibility

1. Required Education

Bachelor's degree in Computer Science, Electrical Engineering, Human-Computer Interaction, or related field