Working Student - AI Agent Architecture

About The Role

• As a Working Student in AI Agent Architecture at Parloa, you will support our Professional Services team in building and improving AI-powered customer service agents. You will work side by side with our Agent Architects, gaining hands-on experience with large language models (LLMs), conversational design, API integrations and real-world enterprise AI deployments. This is not a passive role. From day one, you will contribute to live projects, help shape AI agent behavior, and be part of a team that is redefining how companies interact with their customers. Areas of ownership: Support Agent Architects in the design and testing of AI agent workflows for enterprise customers across a range of industries Research and evaluate LLM prompting strategies, and assist in crafting and refining prompts that align AI agent behavior with customer requirements Support testing of voice agent behavior, including pronunciation adjustments and SSML markup, ensuring agents meet customer brand and language standards Get exposure to API-based system integrations, supporting Agent Architects in connecting customer backends, CRMs, and ticketing systems to deployed agents Help document best practices, how-to guides, and internal knowledge articles that the broader PS team can use and build on Assist with quality assurance: test conversational flows, identify edge cases, and flag issues in agent behavior before customer go-lives Analyze conversation logs and performance data to surface patterns and improvement areas for deployed agents Support the team in preparing customer-facing materials such as scoping documents, training content, and session summaries Stay up to date on developments in the LLM and conversational AI space and share relevant insights with the team Who you are: Currently enrolled in a Bachelor's or Master's program in Computer Science, Computational Linguistics, Cognitive Science, Business Informatics, or a related field Genuine curiosity about AI, large language models, and conversational interfaces, ideally with some hands-on experimentation Interest in conversation design, UX writing, or human-computer interaction, you think about how users experience a dialogue, not just whether it works Structured, analytical thinker who enjoys breaking down complex problems into clear, actionable steps Strong written communication skills in English (German is a plus) Comfortable working with tools like Google Docs, Sheets, and Notion
• experience with APIs or basic scripting (e.g. Python, Javascript) is a plus but not required Proactive and self-driven, you don't wait to be told what to do next Available for 16–20 hours per week, with flexibility around university commitments Our Recruiting Process: Hiring Manager → Technical Interview Parloa is committed to upholding the highest data protection standards for our clients' and employees' data. All our employees are instrumental in ensuring the utmost care, GDPR, and ISO compliance, including ISO 27001, in handling sensitive information. Parloa is an e-verify employer in the USA. Please click here to learn more .
• We provide equal opportunities to all qualified applicants regardless race, gender, sexual orientation, age, religion, national origin, disability status, socioeconomic background and other characteristics.