Senior AI Engineer, Voice Platform
ClickUp, United States
The role
You'll own and evolve the AI systems behind ClickUp's voice platform: real-time streaming transcription, intelligent reformatting, context-aware mention detection, and voice-to-action pipelines. This is a high-impact, hands-on role where you'll push the boundaries of what voice interfaces can do inside a productivity tool used by millions.
What you will do
- Design, build, and optimize real-time speech-to-text pipelines (streaming ASR, VAD, audio processing)
- Improve transcription accuracy through context injection (user names, teams, custom vocabulary, language detection)
- Develop and maintain LLM-powered post-processing (grammar correction, filler removal, mention resolution, formatting)
- Build voice-to-action systems that parse natural language into structured workspace commands
- Evaluate, benchmark, and integrate ASR models (Whisper, AssemblyAI, Fireworks, etc.) for cost, latency, and accuracy