SAP iXp Intern (f/m/d) - Data Analytics & AI Data Preparation

We help the world run better
At SAP, we keep it simple: you bring your best to us, and we'll bring out the best in you. We're builders touching over 20 industries and 80% of global commerce, and we need your unique talents to help shape what's next. The work is challenging – but it matters. You'll find a place where you can be yourself, prioritize your wellbeing, and truly belong. What's in it for you? Constant learning, skill growth, great benefits, and a team that wants you to grow and succeed. 

 

What you´ll build

 

The SAP Internship Experience Program is SAP’s global, strategic, paid internship program that provides university students with opportunities to find purpose in their careers. This is more than an internship; it’s the foundation for a career built on connection, creativity, and impact.

 

Position title: SAP iXp Intern (f/m/d) - Data Analytics & AI Data Preparation
Location: Walldorf
Internship duration: 6 weeks (with option to extend into working student role or thesis collaboration)

 

As a Data Analytics & AI Data Preparation Intern (f/m/d), you will support the enablement of an internal LLM-based chatbot to answers questions about a new data channel. Your primary responsibility will be to prepare, structure, and document data so the LLM can reliably produce accurate answers. You will work at the intersection of data engineering, analytics, and applied AI, guided by strong analytical and mathematical reasoning.

 

• Analyse existing JSON-based datasets in BigQuery and design relational or semi-structured tables and views optimized for LLM consumption.
• Create annotated schemas, including clear column names, descriptions, units, constraints, and example values.
• Establish naming conventions and documentation standards that reduce ambiguity for natural language queries.
• Test the LLM’s ability to answer questions against known ground truth.
• Identify failure modes (e.g., hallucinations, misinterpretation of columns, incorrect joins) and address them through data modeling or prompt improvements.
• Collaborate with stakeholders to define acceptance criteria for answer quality

 

What You’ll Bring 

We’re looking for someone who takes the initiative, perseveres, and stays curious. You like to work on meaningful innovative projects and are energized by lifelong learning. 

 

You are a student in mathematics or a closely related quantitative field. Your strong background in statistics, probability, logic, and analytical reasoning forms the foundation for understanding data structures, modeling decisions, and evaluating the quality of LLM outputs. You enjoy solving abstract and data-driven problems and want hands-on experience at the intersection of mathematics, data engineering, and applied AI.

 

You bring (core requirements):

• Strong foundation in mathematics and statistics.
• Ability to analyze complex data structures and design clear data models.
• Interest in understanding how LLMs reason over structured data.
• Basic programming experience (Python or SQL) or willingness to learn.
• Curiosity, initiative, and a structured, analytical way of thinking.

 

Nice to have:

• SQL experience (especially BigQuery).
• Experience with prompt engineering or LLM reasoning improvement techniques.
• Familiarity with JSON-based datasets, data modeling, or schema design.
• Experience with GitHub or Linux command line.
• Exposure to cloud environments.

 

What you get from us

• A learning-focused environment where your work has direct impact on analytics and AI capabilities.
• Real-world tasks blending analytics, data modeling, and applied AI.
• Close collaboration with experienced developers, data engineers, and architects.
• Fast feedback cycles — your work immediately affects LLM answer quality.
• Flexible working hours and hybrid work options.
• Opportunity to extend the internship into a working-student role or thesis collaboration.

 

Application documents

• Cover letter
• CV
• Transcript of records
• C