About the job
Join the Mercura Team
At Mercura, we are pioneering AI solutions that serve as the backbone of our economy.
Supported by Y Combinator, we have successfully raised a significantly oversubscribed funding round, achieving one of the highest valuations in our cohort. As one of Europe’s rapidly expanding startups, we achieved $2 million in ARR within our inaugural year, and we are now on a mission to reach $10 million ARR by the close of 2026.
Our co-founder, Lukas, hails from a family deeply rooted in the construction industry for over 115 years. Having firsthand experience on construction sites, he witnessed the slow and manual quoting processes prevalent in the industry.
In a world increasingly driven by AI, we are committed to a personal mission: to integrate AI into the core of our economy, empowering the companies that keep our world functioning. We aim to enhance human expertise and allow individuals to focus on endeavors that only humans can accomplish.
Your Role
As an AI/LLM Engineer, you will be instrumental in developing end-to-end agentic AI systems. This dynamic and hands-on position is ideal for engineers who thrive on autonomy, possess robust technical skills, and embody a founder's mindset. You will be responsible for creating dependable AI systems for production, encompassing retrieval and LLM orchestration, tool-using agents, and product integration.
If you are a dedicated innovator who excels at the intersection of LLMs, data systems, AI, data engineering, and full-stack development, this is your chance to influence user interaction with AI in practical workflows.
Key Responsibilities
Agentic Systems: Design and implement LLM-powered agentic systems from experimentation through to production deployment.
Retrieval & Context: Develop retrieval and context pipelines (RAG, hybrid search, structured retrieval) to facilitate reliable reasoning over extensive technical and commercial data.
AI Evaluations: Create evaluation and monitoring systems to assess and enhance AI performance in production.
Data Pipelines: Construct scalable pipelines to process and organize large amounts of unstructured documents and data.
Feedback Mechanisms: Implement automated feedback systems that enable AI to learn from usage data and human insights.
AI Infrastructure: Oversee the architecture and reliability of AI infrastructure.
