🛠 Tech Stack

💼 About This Role

You'll design and scale low-latency speech/LLM pipelines for real-time AI phone agents in healthcare, reducing administrative waste. You'll engineer orchestration layers and reliability systems that handle thousands of daily calls.

🎯 What You'll Do

• Design and build low-latency speech/LLM pipelines
• Develop orchestration layers for voice agent workflows
• Implement reliability systems for production deployment
• Scale platform to handle thousands of concurrent calls

📋 Requirements

• 1-3 years of end-to-end product building experience
• Proficiency in FastAPI (Python) and React (TypeScript)
• Experience managing large-scale distributed systems with async orchestration
• Bachelor's or Master's in Computer Science or related field

✨ Nice to Have

• Familiarity with LLMs, AI agents, or ML models
• Experience with Pipecat for voice agents
• Founder mindset and startup ambition

🎁 Benefits & Perks

• 🚀 Take-home challenge to showcase skills
• 🎯 Fast hiring process with 4 interviews
• 🌍 Opportunity to relocate to New York Office

📨 Hiring Process

Four rounds: initial chat, take-home challenge, solution review with engineers, talk with co-founder, then offer.