Senior AI Engineer, Voice Platform

📋 Description

• • Design, build, and optimize real-time speech-to-text pipelines including streaming ASR, VAD, and audio processing for ClickUp’s voice platform.
• • Improve transcription accuracy by injecting contextual data such as user names, team names, custom vocabulary, and language detection into the ASR system.
• • Develop and maintain LLM-powered post-processing systems to correct grammar, remove filler words, resolve speaker mentions, and reformat transcribed text for clarity and usability.
• • Build voice-to-action pipelines that interpret natural language voice commands and convert them into structured workspace actions within ClickUp’s productivity environment.
• • Evaluate, benchmark, and integrate third-party ASR models (including Whisper, AssemblyAI, Fireworks) based on criteria such as cost, latency, and transcription accuracy.
• • Collaborate with product and platform engineering teams to ship voice features across ClickUp’s MAX Desktop, Mobile, Web, and Browser Extension platforms.
• • Explore and prototype multimodal AI capabilities that combine voice input with screen activity and text input to enable next-generation assistant experiences.
• • Own the end-to-end lifecycle of AI systems powering ClickUp’s voice interface, from research and prototyping to production deployment and performance monitoring.
• • Continuously iterate on voice recognition and command interpretation systems based on user feedback, usage analytics, and emerging AI advancements.
• • Ensure voice features meet scalability, reliability, and privacy standards for a global user base of millions.
• • Work cross-functionally with UX, QA, and infrastructure teams to align voice capabilities with product vision and technical constraints.
• • Stay current with advancements in voice AI, natural language processing, and real-time streaming technologies to inform system design and innovation.
• • Contribute to documentation, model versioning, and monitoring systems to ensure transparency and maintainability of voice AI components.
• • Participate in code reviews, technical design discussions, and sprint planning to ensure high-quality delivery of voice platform features.
• • Advocate for user-centric voice interactions by prioritizing accuracy, speed, and intuitive command structures in all system improvements.
• • Maintain compliance with data privacy and security standards when processing audio and voice data across global regions.
• • Support on-call and incident response for critical voice platform outages or degradation in transcription quality.