Voice Recognition Engineer – Browser-Based Speech Interfaces

New York Technology Partners; Remote; USD 90,000 - 120,000; Full time

Job summary

A prominent technology recruitment firm is seeking a Senior Technical Recruiter/Trainer to develop and enhance voice recognition functionality across multiple browsers. The ideal candidate will have hands-on experience with the Web Speech API and familiarity with major speech frameworks. This remote contract position is suitable for individuals with over 3 years of experience in voice UI or audio processing, focused on optimizing performance and user experience in diverse environments.

Qualifications

• Hands-on experience with Web Speech API and commercial speech frameworks.
• 3+ years in speech recognition, voice UI, or audio processing.
• Understanding of latency, privacy, and security in voice processing.

Responsibilities

• Develop and optimize voice recognition functionality across browsers.
• Ensure user experience across different environments.
• Collaborate to build intuitive voice interactions.

Skills

Familiarity with Web Speech API

Experience in speech recognition

Effective communication with cross-functional teams

Prototyping and problem-solving

Multilingual performance optimization

Tools

ElevenLabs

Deepgram

OpenAI Whisper

Amazon Transcribe

Job description

Senior Technical Recruiter/Trainer @ New York Technology Partners | Resume Writer

Position Type: Contract

Location: Remote

Key Responsibilities

• Develop and optimize voice recognition functionality across Chrome, Edge, Safari, Firefox, and Brave.
• Ensure consistent performance, compatibility, and user experience across desktop, laptop, mobile, and tablet environments.
• Customize and extend the Web Speech API and integrate third‑party speech frameworks, including (but not limited to):
• ElevenLabs (Scribe)
• Deepgram
• OpenAI Whisper API
• Amazon Transcribe / Polly

Performance, Accuracy & Resilience

• Optimize recognition speed, accuracy, and robustness, especially in noisy or low‑bandwidth environments.
• Conduct benchmarking and tuning for real‑world usage scenarios across diverse accents, languages, and acoustic conditions.

User Experience & Accessibility

• Collaborate with product and design teams to build intuitive, inclusive voice interactions.
• Support configurable speech duration thresholds and accessibility best practices for users with varying abilities.
• Partner with technical leads and product managers to align voice capabilities with product roadmap.
• Support client‑facing pilots, demos, and proof‑of‑concept initiatives.

Ideal Candidate Profile

• API Tailor: Deep familiarity with Web Speech API and at least one major commercial speech‑to‑text platform.
• Accuracy‑Focused: Passionate about refining speech models for real‑world reliability, speed, and multilingual performance.
• Collaborative Partner: Communicates effectively with cross‑functional teams (engineering, product, UX).
• Innovative Builder: Enjoys prototyping, problem‑solving, and elevating voice interaction beyond basic transcription.

Required Qualifications

• Must have hands‑on experience with Web Speech API + at least one other commercial speech framework.
• Implement custom logic for error handling, timeout management, speech completion detection, and multilingual support.
• Minimum 3+ years of experience in speech recognition, voice UI, or audio processing.
• Demonstrated work with Web Speech API and at least one of the following: ElevenLabs, AssemblyAI, Deepgram, OpenAI Whisper, Google Cloud STT, Azure Speech, or Amazon Transcribe.
• Understanding of latency, privacy, and security considerations in client‑side voice processing.

Preferred Qualifications

• Experience with WebRTC, MediaRecorder API, or AudioContext.
• Background in natural language understanding (NLU) or voice assistant development.
• Contributions to open‑source speech or accessibility projects.

Seniority Level

Mid‑Senior level

Employment Type

Contract

Job Function

Information Technology and Engineering

Industries

Research Services