> Markdown version of [/jobs/ext/4622576-founding-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4622576-founding-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Founding AI Engineer

- **Company:** True
- **Location:** New York, NY, United States
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Node.Js, Software Product Management, Next.js, Data Streaming, TypeScript, WebRTC, Core Voice Platform, Evaluation Pipelines, Agentic-AI, Information Technology, Playwright
- **Published:** November 7, 2026
- **Apply:** https://www.juju.com/job/28_25303_f0ee765307115ae89e30f6a3830622f5

## About the Role

* Four to seven years of AI engineering experience, including hands-on experience shipping AI agents end to end in production.
 * At least one year working with real-time or voice AI systems, such as WebRTC, LiveKit, streaming, or other low-latency applications.
 * Experience with voice AI, AI sales, browser agents, or another fast-growing AI product, plus familiarity with agent evaluation, observability, and cost optimization.
 * Proficiency in TypeScript, Node.js, and Next.js, with experience in browser automation tools such as Playwright.
 * A computer science degree or another technical background, with strong software engineering fundamentals.
 * Startup founder or founding engineer experience is relevant.
 * Must be based in New York or able to relocate there from the first day.

## Description

Join an early-stage B2B SaaS team as its fifth engineer and lead the technical direction of a real-time AI voice agent for sales. The agent participates in live customer calls, demonstrates products through browser interactions, and follows up with prospects., * Build the agent's reasoning, tool use, memory, and ability to recover when live conversations go off script, while meeting real-time latency requirements.

 * Develop evaluation pipelines and use call data to drive measurable improvements, including fine-tuning where it is effective.
 * Improve browser automation reliability so the agent can demonstrate products in a live browser while speaking with buyers.
 * Ship product features end to end using TypeScript, Node.js, and Next.js, working directly with customers and design partners.
 * Set technical direction for model and method selection, build-versus-buy decisions, and future agent capabilities.