Staff AI Deployment Engineer, Amsterdam

Description

The company runs a trade network that uses AI to help governments and businesses make global supply chains more resilient and secure, while goods keep moving.

This Amsterdam role sits in the implementation team, which takes the platform live inside customer businesses, from signed contract through to measurable value.

The team connects systems, fits the platform into existing business processes, and makes sure the insights change real decisions on the customer side.

You will work with customer people ranging from trade compliance analysts to enterprise IT, and with engineering, data science and product to turn field findings into the next features.

Responsibilities

• Build and launch agentic AI workflows, including multi-step agents, tool and function calls, and automations, that run parts of the customer's operations on live data.
• Link agents to the right data, APIs and systems of record, and set the tools, permissions and guardrails they work within.
• Draft and refine prompts, system instructions and evaluation criteria so agents are dependable in production.
• Add orchestration and human review points so agentic workflows stay safe, traceable and open to correction.
• Track accuracy, cost and latency after launch, and adjust processes as the customer's data and needs change.
• Lead each customer implementation from scoping through configuration, integration, testing, go-live and handover to ongoing support.
• Set up platform features on real customer data and workflows, closing the distance between current product behavior and the customer's needs.
• Write the integrations, data transfers, automations and internal tools that make each rollout work, using AI-assisted coding to speed up delivery.
• Count an implementation as done only when the customer's team uses it in their own process without you present.
• Act as the main technical contact during implementation, leading working sessions, demos and technical deep dives with people from analysts to executives.
• Draw out requirements from customers who cannot yet describe them fully, and turn business problems into concrete technical scope.
• Explain platform behavior, data quality and trade-offs to non-technical people, and pass customer constraints back to the company accurately.
• Set clear expectations on timelines and scope, keeping large enterprise programs on track.
• Coordinate engineering, data science, product and customer success behind each implementation, keeping everyone on one plan.
• Escalate blockers that only another team can clear, make the request precise, and follow it through.
• Send patterns, recurring friction and product gaps from customers back to the product organization.
• Create playbooks, templates and documentation so each implementation goes faster than the last.
• Own the implementation roadmap for your accounts, ordering work by customer value and delivery risk and deciding what ships now and what waits.
• Write requirements, specs and acceptance criteria that engineering and data science can build against.
• Set priorities by customer value and timelines, and work with product on milestones and deadlines.
• Define measurable success criteria for each implementation and track progress against them.

Requirements

• At least 8 years in customer-facing technical delivery, such as implementation, engineering, professional services, technical program management or product management with hands-on scope.
• A record of delivering complex technical projects with external stakeholders against real deadlines and real consequences.
• Strong communication and coordination: you can run a customer session in the morning and align three internal teams in the afternoon.
• Product sense: you ask what problem is really being solved and what the smallest solution would be.
• You can move forward with partial information and unclear direction.
• You prefer automation and repeatable processes over heroic manual effort, and would rather fix a process than repeat it by hand.
• Working proficiency in Python or similar: reading code, writing and debugging scripts, building integrations and shipping small features. Deep systems engineering is not needed.
• Solid SQL and the ability to explore and check data to answer your own questions.
• Hands-on use of AI coding assistants such as Claude Code, Cursor or Copilot as a core part of your workflow, including reviewing their output.
• Hands-on experience building or deploying agentic AI: LLM agents, tool and function calling, retrieval-augmented generation or multi-agent orchestration.
• Skill in prompt engineering and agent evaluation: designing prompts and evals, finding why an agent fails, and improving it to production reliability.
• Familiarity with agent frameworks and protocols such as MCP or LangChain, and with connecting agents to external tools, APIs and data sources.
• Familiarity with REST and Swagger/OpenAPI, Git workflows and cloud-hosted systems.
• Enough knowledge of data pipelines, data modeling and ML systems to scope work, diagnose problems and speak credibly with the engineers building them.
• Experience with global trade, supply chains, customs or trade compliance.
• Background in large enterprise software implementations with many stakeholders over several quarters.
• Exposure to Spark, Databricks or large-scale data processing.
• Experience building internal tools or automation that a team adopted.
• Formal product management experience with roadmaps, specs and stakeholder prioritization.
• Tools and stack: Python, SQL and Spark; Claude Code and other AI development tools used daily; agentic AI including LLM agents, tool calling, MCP, RAG and orchestration frameworks; Docker, Git, Kubernetes, Swagger/OpenAPI, AWS and Azure; Databricks, Elasticsearch, Postgres and Redshift.

Conditions

Based in Amsterdam, with flexibility to travel onsite to customer locations.