About the job
Join Mercura as an AI/LLM Engineering Intern!
At Mercura, we are pioneering AI software that serves as the backbone of our economy. Supported by Y Combinator, we have successfully completed a significantly oversubscribed funding round, achieving one of the highest valuations in our cohort. As one of the fastest-growing startups in Europe, we proudly exceeded $2M in ARR within our first year. We are now on a mission to reach $10M ARR by the end of 2026 and are looking for dedicated team members who are ready to dive deep into this exciting journey.
Our co-founder, Lukas, hails from a family with over 115 years of experience in the construction industry. Having worked on-site himself, he understands the persistent challenges in the industry, especially the slow and manual quoting processes. In an age where AI is becoming integral to industries, we are committed to enhancing human expertise and empowering individuals to focus on what only they can do.
About the Role
As an AI/LLM Engineering Intern, you will be instrumental in developing agentic AI systems from concept to deployment. This dynamic and hands-on position is ideal for engineers who possess a strong technical foundation, a proactive mindset, and a passion for innovation. You will be involved in creating robust AI systems that are production-ready, from retrieval and LLM orchestration to tool-using agents and seamless product integration.
We hold our interns to the same standards as our full-time employees, entrusting them with ownership of projects and ensuring they are individuals we would want to collaborate with in the long term.
If you are a passionate builder who thrives at the intersection of LLMs, data systems, AI, data engineering, and full-stack development, this is an incredible opportunity to influence how users engage with AI in practical workflows.
Your Responsibilities
- Agentic Systems: Design and develop LLM-powered agentic systems from experimentation to production deployment.
- Retrieval & Context: Create retrieval and context pipelines (RAG, hybrid search, structured retrieval) to facilitate reliable reasoning over vast amounts of technical and business data.
- AI Evaluations: Build evaluation and monitoring systems to assess and enhance AI performance in an operational environment.
- Data Pipelines: Construct scalable pipelines for processing and structuring large volumes of unstructured documents and data.
