AI Engineer — Voice Agents

Role overview An AI engineering role focused on building the reasoning layer that makes voice agents production-grade. The work centers on tool use, function calling, and evaluation infrastructure, turning experimental agent behavior into dependable deployed systems.

Responsibilities - Design and implement the reasoning layer that orchestrates tool use and function calling for voice agents - Build and maintain evaluation pipelines that measure agent quality, reliability, and regressions - Take models and prompts from research-grade experiments to production-ready deployments - Debug failure modes in real conversations and harden the agent loop against edge cases - Track developments in LLM and agent research and bring promising techniques into the stack

Requirements - Hands-on experience building with large language models and agent-style systems - Familiarity with tool-use patterns, function calling APIs, and structured outputs - Ability to build evaluation frameworks that inform product and engineering decisions - Strong software engineering fundamentals for shipping reliable production code - Clear thinking about latency, reliability, and quality trade-offs in deployed AI systems

Nice to have - Background in voice, speech, or conversational AI - Experience in ML engineering, applied research, or evaluation infrastructure