About the Role We're building the AI-native distribution layer for the insurance industry — a massive, largely untouched market still running on manual workflows and legacy software. Voice is core to our product, not an afterthought: we operate a real-time voice platform with growing call volume and millions of production traces. As a Voice AI Engineer , you'll own critical pieces of that infrastructure end-to-end, from telephony and ASR/TTS pipelines to the agent-skills layer that powers live calls. We're a fast-moving, distributed team with an AI-native engineering culture. We ship things that work for real customers — not demos. What You'll Do Build and improve our real-time voice platform: call handling, ASR/TTS pipelines, and latency-sensitive audio processing. Work on telephony infrastructure (Twilio/SIP) and the agent/skills layer powering live calls. Drive reliability and latency improvements for a system handling growing call volume at scale. Instrument and monitor voice quality, latency budgets, and failure modes in production. Ship daily using AI coding tools (Claude Code / Codex) as a core part of how you work — we're an AI-native engineering org. What We're Looking For Must-Haves Real-time voice / telephony experience: hands-on with Twilio, SIP, ASR/TTS, or latency-sensitive audio systems. Strong TypeScript / Node.js for production backend systems. High ownership mentality — you take a feature from design to production and support it after launch. Comfortable with distributed/event-driven systems, on-call rotations, incident response, and latency budgets. Proficiency instrumenting and monitoring voice quality and failure modes in production. Eligible to work in LATAM, Ukraine, or Portugal (fully remote); visa sponsorship is not available. Nice-to-Haves Experience building agentic systems in production (tools/skills frameworks, MCP, evals, guardrails). Applied LLM work: fine-tuning, distillation, eval-driven development. Background in insurance, fintech, or another regulated/compliance-heavy vertical. Daily use of AI-assisted development tools (Claude Code, Codex, or similar). Tech Stack Backend: TypeScript, Node.js, NestJS (monorepo) Orchestration: Temporal (Temporal Cloud) Data: PostgreSQL on AWS RDS (multi-tenant), Terraform IaC AI: Anthropic + OpenAI models Platform: AWS, Clerk (auth), Datadog (observability) Tooling: Linear, GitHub, Claude Code + Codex Compensation
Read Less
