The Team:

You will be joining the Knowledge Management team, a specialized unit sitting within Corporate Engagement & Programs (CEP). CEP is a highly collaborative, global department with team members spanning Bangalore, Munich, Madrid, and the US. Our Knowledge Management is fundamentally focused on a critical, forward-looking mission: bringing our vast organizational knowledge up to date across more than 20 distinct tools to ensure it is fully AI-ready. Based in our Bangalore office, you will operate in a dynamic environment characterized by extensive cross-departmental work.

The Role:

As an Intern Knowledge Management Analyst, you will play a key role in transforming how our organization shares and leverages knowledge. You will help transform how our organization shares and leverages knowledge by prototyping Retrieval-Augmented Generation (RAG) frameworks and designing scalable data pipelines. Working with both non-technical stakeholders and data engineering teams, you will make Celonis's organizational knowledge base AI-ready and queryable. This is your opportunity to see your technical projects come to life and make a tangible impact on business operations across Celonis.

The work you’ll do:

• Evaluate & Prototype RAG Solutions: Assist in designing, prototyping, and testing Retrieval-Augmented Generation (RAG) frameworks to make Celonis's organizational knowledge base AI-ready and queryable.
• Data Prep & Optimization: Partner with Data teams to evaluate data chunking strategies, metadata tagging, and vector database management to optimize the retrieval performance of internal KM tools.
• Bridge the Gap Between KM and Tech: Act as a key technical liaison with the Data, Analysis, and Technology teams to translate KM workflow needs into scalable data pipelines and architectural requirements.
• Collaborative Technical Alignment: Participate in cross-functional technical syncs to ensure KM's architectural roadmap aligns perfectly with the broader enterprise technology stack.
• Engage Stakeholders: Propose innovative approaches to knowledge-sharing challenges, facilitate problem-solving sessions, and encourage participation in knowledge management initiatives.

The qualifications you need:

• Academic Background: Graduates from a Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a highly quantitative technical field.
• Foundational CS & RAG Concepts: Solid understanding of data structures, algorithms, and fundamental NLP/LLM concepts—specifically how embedding models, vector search, and retrieval mechanisms work under the hood.
• Technical Tools & Experimentation: Proficient in Python with a solid grasp of agentic architectures. Experience building academic or personal projects involving LLM APIs (like OpenAI, Anthropic, or open-source models via Hugging Face) and vector stores (e.g., Pinecone, Chroma, FAISS) is highly preferred.
• Cross-Functional Communication: Excellent interpersonal and communication skills. 
• Systemic Problem Solving: Passionate about building automated pipelines and intelligent agents to handle data sanitization, eliminating the need for manual, error-prone human tagging.
• Reliability & Drive: Strong time management skills, comfort with public speaking, and the ability to connect complex ideas and solve problems independently.
• Experience: Prior internship experience in relevant technical or data domains is a plus.
• Language: Excellent verbal and written communication in English.