About the role
Space Inch is hiring an AI Engineer to build and operate production LLM services for intelligent B2B workflows. The role covers end-to-end delivery, from service design and implementation through rollout, monitoring, and iteration, with a focus on fast, reliable, grounded recommendations. The team is expanding across several projects using this stack.
The work combines Python and FastAPI services with LLM and retrieval systems, data pipelines, and production observability. You’ll integrate model capabilities into platform APIs and help ensure systems are reliable, measurable, and safe. The position is remote-focused, requires working effectively in CET, and may involve occasional travel, including company retreats in Croatia. It is a B2B engagement for EU applicants outside Croatia.
Highlights
- Build production LLM and RAG services, including retrieval, guardrails, and evaluation.
- Own services through design, rollout, monitoring, and continued improvement.
- Work with Python, FastAPI, APIs, data ingestion, and observability tooling.
- Bring 4-6+ years of software engineering experience and ideally 2+ years shipping LLM/GenAI.
This recap is dataskew's editorial summary, not the company's copy.