Description
We build AI systems that do real work for real businesses. Right now that means voice agents that answer calls for small businesses after hours, and automation workflows that connect the tools those businesses already use. This is not a research role and it is not a prompt writing role. You will build things that talk to actual customers and break in actual production. That is the fun part. What you will do Build voice agents that take live phone calls, answer questions, check availability, and book appointments Design and ship automation workflows that connect CRMs, calendars, booking systems, email, and messaging Wire up LLM tool calling so the agent can actually do things, not just chat Build retrieval systems so agents answer from a client's real documents and policies instead of making things up Set up logging and testing so we know when an agent gives a bad answer, before the client tells us Work directly with clients sometimes: understand their process, then turn it into a working system Deploy, monitor, and keep things running What you need to have Core: Strong Python. You can build and ship a FastAPI service on your own Hands on experience with the OpenAI or Anthropic APIs, including tool calling and structured outputs You have built at least one working automation or agent end to end, and can demo it Comfortable with REST APIs, webhooks, and authentication headaches Git, Docker, and basic cloud deployment Good to have: Voice stack: Vapi, Retell, Twilio, LiveKit, Ele