AI Engineer (LLM Agents & RAG)

Role overview

This role designs and ships AI agents that perform real work for external clients, from answering support questions grounded in client documents to qualifying leads and screening candidates before handing off to a human. The work is production engineering rather than research: every agent built goes live to real users and has to keep working reliably over time.

Responsibilities

- Build LLM-powered agents that answer questions from client data using retrieval, tool use, and clear guardrails - Connect agents to existing client systems such as help desks, CRMs, and messaging platforms - Create evaluation datasets from real conversations and measure quality before and after every change - Monitor live agents, review actual conversations, and improve answers over time - Explain technical trade-offs to non-technical clients in plain language

Requirements

- Track record of shipping LLM-based features to production, including awareness of why some failed - Proficiency in TypeScript or Python, with comfort around APIs, queues, and databases - Genuine care about evaluation and quality measurement, not just demos - Ability to deliver in weekly increments and enjoy showing progress to clients

Nice to have

- Experience with retrieval, embeddings, and vector or hybrid search - Familiarity with Zendesk, Intercom, or the WhatsApp Business Platform

Benefits and work setup

- Remote-first team working with clients in the US, UK, and India - Weekly shipping cadence with direct client demos - Clients own the source code and infrastructure built, so success earns the next project