Description

EVALUATION & TESTING OF AGENTS AND AGENTIC SYSTEMS

In this internship, you'll play a key role in building robust evaluation frameworks for our agentic Al systems. Together with our stakeholders, you'll define strong outputs and use this to inform the creation of comprehensive test sets.

You'll explore LLM-as-a-Judge methodologies and implement structured evaluation approaches that enable data-driven decision-making. Working closely alongside your colleagues in the research and development team, you'll translate evaluation findings into actionable recommendations aligned with industry best practices. Your work will directly inform how we refine and improve our real-world GenAl applications, and give you the opportunity to apply and grow your skills in a professional environment.

MARKET RESEARCH

You'll conduct ongoing research into the rapidly evolving Generative Al landscape, tracking emerging tools, techniques, and approaches relevant to our work. This includes evaluating new solutions, understanding how others are tackling similar challenges, and identifying innovations in Al-powered media workflows to ensure our team maintains a clear understanding of developments in relevant topics.

TEAM & CULTURE

Culture is key to our team. As our intern, you’ll prove yourself as a communicative team player. You’re interested in gaining new experiences, learning new things, and discovering opportunities we can explore together. You become part of a culture of appreciation and respect, where it is safe to make mistakes, to learn and to improve.

Qualifications

• Advanced undergraduate student, postgraduate student, or recent graduates (Bachelor’s / Master's degree) in Computer Science, Data Science, Engineering, or a related field

• Fluent in English, German is a plus

• Solid understanding of LLMs and Generative AI, enabling you to contribute to prompt design, evaluation, and structured testing of agentic AI systems

• Initial hands‑on experience with prompt engineering and prompting strategies
• Familiarity with evaluation methodologies, including traditional ML metrics or structured qualitative assessment frameworks
• Programming and scripting skills (e.g., Python) to support evaluation frameworks, example test set creation, and exploration of LLM‑as‑a‑Judge approaches
• Strong interest in cloud technologies, paired with a continuous learning mindset and curiosity for emerging tools and methods
• Willingness to challenge the status quo and explore new technologies, combined with analytical problem‑solving abilities
• Self‑driven, communicative team player with an affinity for media & technology and a user‑centric, research‑oriented mindset

Additional Info

As an employer, we value diversity and support people in developing their potential and strengths, realizing their ideas and seizing opportunities. We believe passionately that employing a diverse workforce is central to our success. We welcome applications from all members of society irrespective of age, skin colour, religion, gender, sexual orientation or origin.

Due to legal reasons, we are obliged to disclose the minimum salary according to the collective agreement for this position, which is € 2.221,00 gross per month.

Company Description

Are you passionate about Artificial Intelligence and eager to gain hands‑on experience in building real solutions with Generative AI?

This internship offers you the opportunity to join us for six months as a Generative AI Intern, where you’ll learn from experienced colleagues and actively contribute to meaningful projects in a dynamic, forward‑thinking environment.

Red Bull Media House is an award-winning, globally distributed multi-platform media company on a mission to inspire with ‘beyond the ordinary’ stories - both direct-to-consumer and through partnerships. With a focus on sports, culture and lifestyle content, Red Bull Media House offers a wide range of premium media products across TV, mobile, digital, audio, and print. www.redbullmediahouse.com