Generative AI Evaluation Intern – Data & Metrics

D One; Zürich; On-site; CHF 28,000 - 39,000; Full time

Benefits offered by this job

Mentoring by senior consultants

D ONE Academy access

Own topic to own

Offsite socialising events

Path to consultant role

Job summary

D ONE Value Creation AG in Zürich invites motivated students (Bachelor, Master, or PhD) to join a fixed-term internship focused on evaluating generative AI systems. You will work independently on a topic, translate fuzzy questions into measurable metrics, and make those measurements repeatable.

Your work will cover reviewing evaluation methods, implementing Python code, building test data, analyzing results, and presenting conclusions to both technical and non-technical audiences.

Qualifications

• Currently enrolled in a Bachelor's, Master's or PhD programme in Computer Science, Data Science, or related fields.
• Interest in data-to-value creation across industries.
• Results-oriented, pragmatic attitude.
• Experience with large data sets and databases.
• Knowledge of Python, SQL, Git, Spark and cloud platforms.
• Excellent English communication; German is a plus.

Responsibilities

• Review evaluation methodology for retrieval-augmented and generative systems.
• Design and implement automated evaluation logic in Python.
• Build and curate test data sets, including gold standards and synthetic cases.
• Analyse results statistically and draw defendable conclusions.
• Document work and present to technical and non-technical audiences.

Skills

Python

SQL

Git

Spark

Cloud platforms

Large data sets

English communication

German

Education

BSc/MSc/PhD in Computer Science or related

Tools

RAGAS

DeepEval

Promptfoo

LangSmith

Job description

D ONE Value Creation AG in Zürich invites motivated students (Bachelor, Master, or PhD) to join a fixed-term internship focused on evaluating generative AI systems. You will work independently on a topic, translate fuzzy questions into measurable metrics, and make those measurements repeatable.

Your work will cover reviewing evaluation methods, implementing Python code, building test data, analyzing results, and presenting conclusions to both technical and non-technical audiences.