AI Solutions Engineer

Location: Amsterdam, Netherlands

Company

Adaptfy is a data and analytics joint venture formed by SHV and hirify.global, delivering AI, data, and analytics solutions across SHV’s international portfolio of companies.

What you will do

• Design, implement, and refine AI solutions and products from prototyping through production deployment.
• Build and maintain the organization’s AI-focused context layer, including knowledge graphs, ontologies, governance graphs, data lineage frameworks, and RAG pipelines.
• Apply prompt, context, memory, and harness engineering techniques to improve the performance and reliability of production AI models.
• Translate business requirements and operational challenges into AI-enabled use cases, workflows, and intelligent automation.
• Contribute to robust, scalable agentic AI systems and orchestration architectures aligned with enterprise governance requirements.
• Document methodologies, prompt libraries, and context engineering standards to create reusable institutional knowledge.

Requirements

• 1–4 years of professional experience as a software engineer, data scientist, data engineer, or AI engineer.
• Strong programming skills in at least one modern language, Git proficiency, and solid software engineering practices.
• Hands-on experience building LLM-based systems, including prompt engineering and an orchestration framework such as LangChain, LlamaIndex, or LangGraph.
• Strong understanding of Retrieval-Augmented Generation pipelines and data quality, lineage, semantics, and governance.
• Awareness of leading LLMs, multimodal models, agentic frameworks, and orchestration tools.
• Fluent English is required, along with the ability to explain complex AI concepts to non-specialist audiences.

Nice to have

• Python experience.
• Practical experience with knowledge graphs, ontologies, or semantic data models.
• Experience in international, consulting, or scale-up environments.
• Additional language skills.

Culture & Benefits

• Opportunity to help define applied AI practices within a large organization.
• Technical exposure across the full AI stack, from data foundations and knowledge graphs to agentic systems and LLM orchestration.
• Collaboration with central and local data teams and business stakeholders.
• Work on reusable AI assets and infrastructure designed to create long-term business value at scale.
• Culture of experimentation, continuous learning, knowledge sharing, diversity, equity, inclusion, and belonging.