ML Engineering Intern: Build AI Evaluation Pipelines

Zendesk GmbH (Germany); Germany (OH); Hybrid; USD 2,755,000 - 4,959,000; Full time

Job summary

Zendesk GmbH is seeking a Machine Learning Engineering Intern to work on both back-end and front-end of the Zendesk Explore platform. You will join a team building features for AI Agents and be responsible for creating high-quality datasets to evaluate agent performance.

You will develop evaluation logic using Python and LLM-based techniques, iterating prompts and metrics to align automated scores with human feedback and improve agent behavior.

Qualifications

• Student pursuing a degree in a relevant field.
• Comfort with Python or TypeScript/JavaScript.
• Interest in AI, NLP, LLMs and evaluating AI agents.

Responsibilities

• Join a team building product features for AI Agents on Zendesk Explore.
• Build datasets and frameworks to measure AI agent quality.
• Create golden datasets from real-world conversations for benchmarking.
• Develop evaluation logic using LLM-as-Judge techniques and compare with human feedback.

Skills

Python

TypeScript/JavaScript

NLP / LLMs

Communication

Education

Student status

Job description

Zendesk GmbH is seeking a Machine Learning Engineering Intern to work on both back-end and front-end of the Zendesk Explore platform. You will join a team building features for AI Agents and be responsible for creating high-quality datasets to evaluate agent performance.

You will develop evaluation logic using Python and LLM-based techniques, iterating prompts and metrics to align automated scores with human feedback and improve agent behavior.