AI/LLM Engineer

Mercura builds AI software for technical suppliers - the distributors and manufacturers who supply contractors to build new hospitals, schools, homes, and power plants.

This industry runs on expertise built over decades. But too much of that expertise gets buried in manual work - processing vague requests, keying data into ERPs, answering phone calls - instead of serving customers. Some of the best teams turn down up to 30% of incoming business simply because they can't keep up. Mercura changes that.

Backed by Y Combinator, we surpassed $2M in ARR in our first year. Now we're looking for people ready to go all-in to reach our next milestone: $10M ARR by end of 2026.

One of our co-founders, Lukas, grew up in a fourth-generation trades family and worked on construction sites himself. That's where he learned first-hand how slow and manual this work still is. No skilled person should spend their time on work that software should handle. We're building the tools that give experts their time back.

About the role:

As an AI/LLM Engineer, you will play a key role in building agentic AI systems end-to-end. This is a fast-paced, hands-on role for engineers with high agency, strong technical depth and founder mindset. You'll work on building reliable AI systems in production - from retrieval and LLM orchestration to tool-using agents and product integration.

What you will be working on:

• Agentic Systems: Design and build LLM-powered agentic systems end-to-end, from experimentation to production deployment
• Retrieval & Context: Build retrieval and context pipelines (RAG, hybrid search, structured retrieval) to enable reliable reasoning over large volumes of technical and commercial data
• AI Evals: Develop evaluation and monitoring systems to measure and improve AI performance in production
• Data Pipelines: Build scalable pipelines to process and structure large volumes of unstructured documents and data
• Feedback Loops: Implement automated feedback pipelines that allow AI systems to learn from usage data and human feedback
• AI Infra: Own the architecture and reliability of AI systems in production, ensuring they are fast, scalable, and robust
• Product Integration: Collaborate with other engineers to deeply integrate AI capabilities into the product experience

What we're looking for:

• Proven track record of architecting and building complex, AI/LLM-powered systems or agents in production, including model serving, orchestration of agent workflows, monitoring, and scaling AI workloads
• Designing systems that process and structure large volumes of unstructured data
• Developing evaluation and feedback loops to measure and improve AI system performance
• Experience with Python is required
• Experience in full-stack development (React / Typescript / FastAPI) is a plus
• High agency & ownership; mission-driven; product mindset; want to work in-person in Munich

What we offer:

• Learn to build a company - over five Mercura alumni have gone on to found their own companies and raise millions after their time with us
• Guaranteed career advancement opportunities in a rapidly growing team
• Real shares in our company with the most favorable tax treatment - no VSOP/ESOP
• Free team dinner (up to 4x/week)
• UrbanSportsClub membership and access to a company bike
• Easy relocation to Munich - office in Werk1 Startup Incubator with a 1-bedroom apartment right next to the office for just EUR 800/month
• Access to any AI or productivity tools you need

Your team & mentors include Sean (Co-Founder & CTO, Silver Medallist at the IPhO), Ben (prev. AI Engineer at Aleph Alpha), Mark (prev. SWE at Capital One, Cambridge Graduate), and mentors Rohan Ramanath (GM AI Product at Nubank) and Daniel Ribeiro Silva (Senior Director of ML at Nubank).