AI Engineer (Data & LLM pipelines)

Grantific; Utrecht; Hybrid; EUR 80,000 - 110,000; Full time

Benefits offered by this job

Hybrid work Utrecht

Competitive salary

Laptop provided

Travel card

30% ruling support

Snacks in office

Job summary

Grantific is seeking an AI Engineer to design, build and operate the data pipelines and AI infrastructure powering our grant matching platform. You will process large volumes of European grant data from APIs, scraping and public sources and develop production-grade LLM workflows for extraction, retrieval and matching.

The role blends AI, data engineering and product development, requires ownership and collaboration with cross-functional teams in a fast-paced startup environment in the

Qualifications

• 3+ years in software/data/AI engineering or related role
• Proficient Python including async programming
• Experience building production data systems end-to-end

Responsibilities

• Design and maintain scalable data pipelines for European grant data
• Integrate and process heterogeneous data sources incl. APIs, scraping pipelines, public datasets
• Build production-grade LLM pipelines for retrieval, extraction and matching
• Improve data quality via deduplication and entity resolution
• Develop evaluation frameworks for LLM performance and faithfulness scoring
• Collaborate with product, engineering and domain experts
• Own the data infrastructure behind the grant matching platform end-to-end
• Continuously improve scalability and reliability of AI systems

Skills

Python

Async programming

SQL

Schema design

Data engineering

AI engineering

LLM pipelines

Retrieval

Entity resolution

Data pipelines

Communication

Collaboration

Education

Bachelor's degree in CS/Engineering

Tools

Vector databases

Job description

Please note: This position is only open to applicants who are based in the Netherlands and able to work regularly from our office in Utrecht. We do not offer visa sponsorship for this position.

About Grantific

Grantific helps innovative companies find, manage, and secure funding opportunities more efficiently. Our technology simplifies and automates the grant application process, helping organizations identify funding opportunities faster and manage applications more efficiently. As we continue to grow, we are looking for an ambitious AI engineer that will take the responsibility for our advanced grant matching solution within our platform. We started by automating the process of writing grant proposals, and the grant matching platform connects applicants to the funding opportunities most relevant to them. To make that possible, we are building a robust and scalable corpus of European grant calls powered by modern AI and data infrastructure. And that's where you come in.

About the Role

As an AI Engineer at Grantific, you will be responsible for designing, building, and maintaining the data pipelines and AI infrastructure powering our matching platform. You will work on integrating and processing large volumes of heterogeneous grant data from APIs, scraping pipelines, and external sources, while building production-grade LLM workflows for extraction, retrieval, and matching. This role is ideal for someone who enjoys solving complex engineering challenges, takes ownership, and wants to work at the intersection of AI, data engineering, and product development.

Key Responsibilities

• Design and maintain scalable data pipelines for European grant data
• Integrate and process heterogeneous data sources including APIs, scraping pipelines, and public datasets
• Build and optimize production-grade LLM pipelines for retrieval, extraction, and matching
• Improve data quality through deduplication, entity resolution, and schema design
• Develop evaluation frameworks for LLM performance, hallucination detection, and faithfulness scoring
• Collaborate closely with product, engineering, and domain experts
• Take ownership of the data infrastructure behind the grant matching platform end-to-end
• Continuously improve scalability, reliability, and performance of AI systems

What we're looking for

• 3+ years of experience in software engineering, data engineering, AI engineering, or a related role
• Strong Python experience, including async programming, SQL, and schema design
• Experience building and maintaining production data systems end-to-end
• Hands-on experience with heterogeneous data integration, APIs, and web scraping
• Experience with deduplication and entity resolution in production environments
• Experience building production LLM pipelines, including retrieval and structured extraction
• Understanding of LLM evaluation methods such as hallucination quantification and faithfulness scoring
• Experience with vector databases is a strong plus
• Proactive, independent, and collaborative working style
• Strong communication skills and ability to translate complex problems into practical solutions
• Academic background is a plus

What we offer

• The opportunity to work on cutting-edge AI products with real-world impact
• A startup environment with ambitious and driven colleagues
• Freedom and flexibility to do your best work
• Significant growth opportunities as the company scales
• A strong culture of learning, curiosity, and continuous improvement
• Direct impact on innovation and research funding across Europe
• Hybrid working environment with three office days per week in Utrecht
• Competitive salary and secondary benefits package
• Laptop, travel card, and all essential equipment provided
• 30% ruling support available for eligible international hires
• And yes - snacks in the office