AI Engineer (Agent Platform)

Location: Hybrid (Amsterdam Office) | Salary: €70K – €110K

Who we are

Bonnie is the AI assistant that answers the phone for local businesses (serving the Hospitality sector) WhatsApp and chat. 1000+ businesses in 15 countries use us today. Millions of conversations, each one a real customer who expects an answer now.

Engineering is small and broad: a handful of engineers across data, APIs, DevOps, AI agents and cloud, plus a designer. Everyone ships to production, and everyone talks to the businesses using Bonnie. The loop from a change to a restaurant owner telling you what they make of it runs in days, not quarters.

The role

You own the decision layer: the tool-sets the assistant calls mid-conversation, the orchestration and routing across models, the configuration platform that lets every business behave differently, and the evaluation system that keeps all of it reliable at millions of conversations.

We are hiring multiple people into this scope — one senior, one medior — so the depth we expect scales with the level you come in at.

The stack: Python and FastAPI, LiteLLM for model routing, language tools (LangFuse, Langsmith) for tracing and evaluation, MySQL and Postgres, queues and workers, Docker. Claude Code, Codex and Cursor in the daily loop.

Your first project is the evaluation harness: replaying real conversations against a change and scoring what comes out. It is the fastest way to learn the product. Within a month you will have touched the call path, the tool-sets and the data behind them.

What you’ll do

• Design and own Bonnie’s tool-sets — availability, reservations, modifications, escalation — including their contracts, failure behaviour and latency budgets.
• Build the evaluation system. Replay real conversations, score outcomes, catch regressions before they ship. This is how Bonnie stays reliable as volume grows, and it is the highest-leverage work on the team.
• Build the configuration platform: a schema-driven model built from blocks for per-business behaviour — versioned, validated, and safe to change without a deploy, so a change of tone or opening hours never needs an engineer.
• Orchestrate the models. Routing, fallbacks, guardrails, and the cost and latency trade-offs between them.
• Work on the call path. Latency budgets, turn-taking and interruptions, transfers, SIP, load balancing across STT and TTS providers. A hundred milliseconds is audible, and this is where the agent meets the phone line.
• Run what you build. Deploys, observability, and a two-week support shift that comes round about once every two months. Outside office hours is light (historically a few hours on an incidental Saturday, roughly once a quarter). Mostly we keep an eye because we built Bonnie and we care how it behaves, not because a rota says so.

What you bring

• 3+ years building and operating production backends, at least one of them on LLM-powered systems real users depended on. For the senior role: 5+ years, and a system you designed rather than contributed to.
• Agentic systems, and where they break. Tool calling, multi-step orchestration, structured outputs, retries, partial failure, context management. These are distributed systems problems with a new failure mode.
• A point of view on evaluation. You have had to prove an AI system got better, and you know why a good demo is not proof.
• Async Python and API design. Contracts, idempotency, timeouts and failure modes before the handler. Comfortable in a relational database and a queue.
• AI-native, with accountability. Coding agents are in our daily loop. Use them, and explain, test and own what they produce.
• Comfort in a codebase you did not write. Ours got us to 500+ customers at speed, and it shows. We are carving it into clear domains while shipping.
• Amsterdam area and EU work authorization. We do not sponsor visas today and we want to offer a fixed contract, no freelance.

Extra credit: voice, telephony or real-time systems (Twilio, SIP, LiveKit, WebRTC) · data engineering · infrastructure as code · open-source work on agents or evals · Dutch.

Not ideal if

• Your LLM experience is prompts and a chat wrapper, and keeping it working was never the hard part.
• You want a spec handed over. We scope our own work here.
• You need a settled codebase and a fixed process.
• You want your work to stop at the merge. We built Bonnie and we keep an eye on it, which occasionally means outside office hours.

How we hire

1. Intro call, 30 minutes online. What you have built, and why it was hard.
2. Technical conversation, 60 minutes at the office. Your work first, then a real piece of ours.
3. Case, 2 hours of your time, then 30 minutes presenting your choices. We tell you up front what we score.
4. Culture chat with one of our founders, 45 minutes. No more assessment (the last check, both ways).
5. Offer.

Under three weeks from first call to decision, and an answer within three working days at every step.

What we offer

• Salary: €70-110K
• Gross per year, depending on level, including 8% holiday allowance
• 25 holiday days a year
• Meaningful equity through our ESOP.
• A brand new office on the Herengracht trust us, its nicee.
• Full setup: a fresh MacBook, the tools you ask for, and a budget for the rest.
• Quarterly team events, and the whole team together every few months.
• Real customers: Loetje, 3WO, Dudok, Ron Gastrobar and a growing list across 14 countries.

Ready to build?

Send your CV, a link or two to things you have built, and one sentence on the most interesting thing you shipped this year.