This is the role our delivery model is built around. You lead the engineering inside a client operation for the length of an engagement, usually one or two at a time, and you own the system from the first workflow audit to the day it runs in production without us.
This is an on-site role. You work at the client's locations in Europe through audits and build phases, so travel is a regular part of every active engagement.
The scope is broad and the room is senior. In one week you might map how an operations team really handles exceptions, talk a director out of a project that will not pay off, then spend two days on the retry semantics of a tool-calling loop. If you like the engineering but not the room, this is not the right seat.
What you will do
- Lead workflow audits with the client's operations and finance leads: map what actually happens against what the process document claims, and decide which workflow is worth rebuilding first
- Set the architecture for systems that run inside the ERP, CRM and data platforms a client already has, without demanding a migration
- Own the production path: orchestration, evaluation, cost guardrails, observability, security review and the handover the client's team runs from
- Be the senior technical counterpart for the client's CIO, architects and the engineers who will inherit the system, including the ones who doubt it will work
- Coach the engineers on your engagement, and bring what you learn back into how we scope and run the next one
What we look for
- 7+ years building production software, including at least two years shipping LLM applications that other people depended on
- Strong Python, and the judgement to know when a problem does not need an agent at all
- Deep experience with retrieval, tool use and structured output, and with the failure modes each of them brings
- Enterprise integration experience: ERPs, identity, network constraints, change control and security reviews
- Cloud infrastructure on Azure, AWS or GCP, and the CI/CD that keeps a deployment honest
- The communication to explain a trade-off to a CFO and a retry policy to a staff engineer on the same afternoon
Nice to have
- Experience in industries outside software, such as manufacturing, distribution, healthcare or financial services
- You have inherited someone else's stalled AI pilot and got it into production
- Forward deployed or technical consulting experience at a product or services firm
Your first six months
- Month 1: join a live engagement as its technical lead and run the next workflow audit
- Month 3: own an engagement end to end, including the client relationship and the architecture decisions
- Month 6: your system is in production, the client's team runs it, and you are shaping how we scope and staff the next engagement