Voice AI Engineer

Reports to: Head of Engineering / CTO

About Superagent AI

Superagent AI is building the AI-native distribution layer for insurance — a $7T industry still run on manual workflows and legacy software. We're an early-stage, fast-moving team reimagining how insurance is sold, serviced, and supported, with AI at the core. Backed by top-tier VCs, we're an international team of exited founders, builders, and technologists. Already trusted by 100+ agencies, we run a real-time voice platform with growing call volume and millions of traces - voice is core to the product, not a bolt-on.

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 that powers live calls.
• Improve reliability and latency for a system handling growing call volume and millions of traces.
• Instrument and monitor voice quality, latency budgets, and failure modes in production.
• Ship daily using Claude Code / Codex as a core part of how you work - we're an AI-native engineering org.

About you (must-haves)

• High ownership and hands-on experience - you take a feature from design to production and support it after ship.
• Real-time voice / telephony experience: Twilio, SIP, ASR/TTS, or latency-sensitive audio systems.
• Strong in TypeScript/Node for production backend systems.
• Comfortable with distributed/event-driven systems and production reliability (on-call, incidents, latency budgets).
• You use Claude Code / Codex or similar AI coding tools daily.

Bonus

• Experience building agentic systems in production - tools/skills frameworks, MCP, evals, guardrails.
• Applied LLM work: fine-tuning, distillation, eval-driven development.
• Insurance, fintech, or another regulated/compliance-heavy vertical.

Our stack

Backend: TypeScript, Node, 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) · How we ship: Linear, GitHub, Claude Code + Codex as part of daily engineering.

How we work

Fast-moving distributed team with an AI-native engineering culture. We're closer to our customers than most competitors - that's our edge, and it drives how we prioritize. We ship things that work for real agencies, not demos.