Senior AI Engineer, Voice Platform

ClickUp ClickUp · Enterprise · United States · Engineering

Senior AI Engineer to own and evolve the AI systems behind ClickUp's voice platform, including real-time streaming transcription, intelligent reformatting, context-aware mention detection, and voice-to-action pipelines. The role involves designing, building, and optimizing speech-to-text pipelines, improving transcription accuracy, developing LLM-powered post-processing, building voice-to-action systems, and evaluating ASR models. Collaboration with product and platform teams to ship voice features across various platforms and exploration of multimodal AI capabilities are also key responsibilities.

What you'd actually do

  1. Design, build, and optimize real-time speech-to-text pipelines (streaming ASR, VAD, audio processing)
  2. Improve transcription accuracy through context injection (user names, teams, custom vocabulary, language detection)
  3. Develop and maintain LLM-powered post-processing (grammar correction, filler removal, mention resolution, formatting)
  4. Build voice-to-action systems that parse natural language into structured workspace commands
  5. Evaluate, benchmark, and integrate ASR models (Whisper, AssemblyAI, Fireworks, etc.) for cost, latency, and accuracy

Skills

Required

  • Speech-to-text (ASR)
  • LLM post-processing
  • Natural Language Processing (NLP)
  • Voice interface design
  • System design and optimization
  • Model evaluation and benchmarking

Nice to have

  • Multimodal AI
  • Product integration

What the JD emphasized

  • real-time streaming transcription
  • voice-to-action pipelines
  • speech-to-text pipelines
  • LLM-powered post-processing
  • voice-to-action systems
  • ASR models

Other signals

  • voice platform
  • speech-to-text
  • LLM-powered post-processing
  • voice-to-action systems
  • ASR models