Senior AI Engineer, Voice Platform

About the role

At ClickUp we are building an AI‑native workspace that unifies tasks, docs, chat, calendar and search. The Senior AI Engineer, Voice Platform will own and evolve the AI systems that power real‑time voice interactions across our desktop, mobile, web and browser extension products.

Key responsibilities

• Design, build, and optimise real‑time speech‑to‑text pipelines, including streaming ASR, voice activity detection and audio processing.
• Improve transcription accuracy by injecting contextual information such as user names, teams, custom vocabularies and language detection.
• Develop and maintain LLM‑powered post‑processing for grammar correction, filler removal, mention resolution and formatting.
• Build voice‑to‑action systems that translate natural language into structured workspace commands.
• Evaluate, benchmark and integrate ASR models (e.g., Whisper, AssemblyAI, Fireworks) focusing on cost, latency and accuracy.
• Collaborate with product and platform teams to ship voice features across multiple platforms.

Required skills

• Automatic Speech Recognition (ASR) and streaming pipelines
• Voice Activity Detection (VAD) and audio processing
• Large Language Models (LLM) for post‑processing
• Experience with Whisper, AssemblyAI or Fireworks models
• Contextual language injection and custom vocabulary handling