🛠 Tech Stack

💼 About This Role

You'll design and scale the low-latency speech/LLM pipelines and orchestration layers for real-time AI voice agents in healthcare. Your work will power systems that adapt instantly to high-stakes conversations. You'll be at the center of deploying production-grade software that eliminates administrative waste.

🎯 What You'll Do

• Build and deploy production-grade software end-to-end
• Design low-latency speech/LLM pipelines for voice agents
• Scale orchestration layers and reliability systems
• Collaborate on user-facing AI products

📋 Requirements

• 3-5 years of experience building and deploying production software
• Solid understanding of FastAPI (Python) or equivalents
• Experience with LLMs or AI agents in user-facing products
• Proficiency in React (TypeScript) frontend

✨ Nice to Have

• Familiarity with large-scale distributed systems
• Experience with async workload orchestration

📨 Hiring Process

Initial conversation, take-home challenge, solution review with engineers, talk with co-founder, then offer.