Senior AI Engineer, Voice Platform
ClickUp · Remote · United States ·
COMPENSATION
$200k – $250k
Listed on the employer's job board (Ashby)
- Senior AI Engineer
- Fully remote
- Real-time ASR pipelines
- LLM post-processing
- Voice-to-action systems
You will own the AI infrastructure behind ClickUp's voice platform, handling real-time streaming transcription and intelligent reformatting. The team works on pushing the boundaries of voice interfaces within a tool used by millions, integrating context-driven AI into tasks, docs, and chat.
What you'll do
- Design and optimize real-time speech-to-text pipelines including streaming ASR and VAD
- Improve transcription accuracy using context injection like user names and custom vocabulary
- Develop LLM-powered post-processing for grammar correction and filler removal
- Build systems that parse natural language into structured workspace commands
- Benchmark and integrate ASR models based on cost, latency, and accuracy metrics
- Collaborate with product teams to ship voice features across desktop, mobile, and web
- Explore multimodal AI capabilities combining screen, voice, and text inputs
What you'll need
- Proven experience building real-time speech-to-text or audio processing systems
- Strong background in optimizing ASR models for latency and accuracy
- Experience with LLMs for text post-processing and natural language understanding
- Ability to evaluate and integrate third-party AI services effectively
- Daily leverage of AI tools and demonstrated AI fluency
- Experience collaborating with cross-functional product and platform teams
Stack
- Whisper
- AssemblyAI
- Fireworks
- ASR
- VAD
- LLM
How you'll work
- Fully remote position
- AI fluency evaluated during hiring process
- Visa sponsorship considered for engineering roles based on business needs