🛠 Tech Stack

💼 About This Role

You'll build and improve real-time AI voice agent systems that power automated calls for thousands of businesses. You'll own critical parts of the speech pipeline, LLM conversation logic, and agent configuration, making AI interactions feel natural and reliable. This role offers the chance to work on cutting-edge voice AI at scale with a fast-moving, product-driven team.

🎯 What You'll Do

• Develop real-time audio buffering and streaming systems for low-latency speech.
• Build LLM prompt construction and context management for natural conversations.
• Design action framework for configurable API calls and auth management.
• Implement knowledge ingestion and retrieval for dynamic agent memory.

📋 Requirements

• 5+ years building production backend systems in Python or TypeScript.
• Experience with real-time systems including buffering, streaming, and latency optimization.
• Proven work with LLMs or AI/ML systems in production involving prompt engineering and function calling.
• Deep knowledge of event-driven architectures, message queues, and async processing.

✨ Nice to Have

• Experience with voice, audio, or telephony systems.
• Prior work with STT or TTS providers and models.
• Familiarity with LLM evaluation frameworks and quality metrics.

🎁 Benefits & Perks

• 🏖️ Unlimited PTO
• 📈 Stock options
• 💻 Remote-friendly hybrid model
• 🏥 Health insurance
• 📚 Learning budget