Used Tools & Technologies
GenAIRequired Skills & Competences
Tag name is followed by "@" symbol and proficiency level value.
About proficiency levels:
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
Communication @ 3
LLM @ 3
Audit @ 3
Compliance @ 3
Generative AI @ 3
AI @ 3
Prompt Engineering @ 3
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
Details
We are seeking a dynamic AI Agent Developer Intern to support the Intelligent Automation team within the Process Excellence & Digitalization department. This delivery-focused role offers a unique opportunity to build enterprise-grade generative AI solutions using Copilot Studio AI agents to transform operations at ING Wholesale Banking.
Responsibilities
- Build Microsoft Copilot Studio Agents
- Design and develop AI agents to solve real operational use cases
- Configure topics, instructions, flows, and knowledge sources in Copilot Studio
- Translate business requirements into agent logic and workflows
- Prompt Engineering & LLM Optimization
- Design and refine prompts and structured instructions to improve output quality
- Test prompt variations and measure improvements in accuracy and consistency
- Build reusable prompt patterns and agent templates
- Ensure Safety, Guardrails & Compliance
- Implement guardrails to prevent prompt injection or instruction override
- Apply hallucination minimization techniques (e.g. grounding, validation checks, structured outputs)
- Ensure agents operate strictly within defined scope and governance controls
- Documentation & Knowledge Sharing
- Document agent design, prompts, and decision logic
- Maintain clear audit trails for experiments and outcomes
- Present results and improvements to stakeholders
Requirements
- Hands-on experience with building low-code agents in Microsoft Copilot Studio in combination with good understanding of Microsoft Power Platform environment
- Strong working knowledge of generative AI and Large Language Models (LLMs)
- Practical experience with prompt engineering beyond basic usage
- Analytical mindset with problem-solving skills and attention to detail
- Excellent communication skills and ability to work collaboratively in a dynamic environment
Benefits
- Opportunity to contribute to impactful projects that shape the AI-first future of operations
- Mentorship from experienced professionals in the fields of automation and AI
- A collaborative, innovative, and inclusive workplace culture
- Internship allowance of 700 EUR based on 36 hours work week
- Your own work laptop
- Hybrid working to blend home working for focus and office working for collaboration and co-creation
- Personal growth and challenging work with endless possibilities
- An informal working environment with innovative colleagues
During the duration of your internship at ING, it is mandatory to be enrolled at a Dutch university (or EU-university for EU passport holders).