Summary
✨ AI‑Generated
Build production-grade AI applications from the first prototype through deployment and ongoing monitoring. You will design retrieval and prompting systems, work with embeddings and vector databases, create evaluation frameworks, develop backend APIs, and optimize live systems for quality, accuracy, cost, and latency.
Highlights
End-to-end AI engineering role focused on taking LLM applications from prototype to reliable production systems. The work spans retrieval, evaluation, backend services, deployment, monitoring, and systematic improvement of quality, accuracy, cost, and latency.
Description
This role is for an engineer who builds LLM-powered applications and takes them into production.
Not a chatbot demo, but AI systems that are reliable, measurable and used every day.
You work in small teams, from the first prototype through to a product people actually adopt.
The role
You build AI applications end-to-end: from retrieval and prompting to evaluation, deployment and monitoring.
You decide how LLMs fit into existing systems and processes, and you make sure they keep performing once they are live.
Your work includes:
Building LLM applications using RAG, prompt engineering, tool use and agent orchestrationDesigning retrieval pipelines: chunking, embeddings, hybrid search and re-ranking on vector databasesSetting up evaluation frameworks to measure quality, accuracy and hallucination, and improving on them systematicallyBuilding the backend services and APIs that bring AI into existing applications and workflowsMonitoring cost, latency and quality in production, and adding guardrails where neededPresenting results and trade-offs to both technical and non-technical audiences
What we look for
An MSc in a relevant field such as AI, Computer Science, Data Science or EngineeringAt least 2 years of experience as an AI Engineer, Software Engineer or ML EngineerStrong Python and solid software engineering fundamentals: clean, tested and maintainable codeHands-on experience building with LLM APIs such as OpenAI, Anthropic, Azure OpenAI or AWS BedrockExperience with frameworks such as LangChain, LangGraph, LlamaIndex or Pydantic AIExperience with vector databases or search, such as pgvector, Qdrant, Weaviate or Azure AI SearchExperience building APIs (e.g.
FastAPI) and with Git, Docker and CI/CD on a cloud platformExperience taking AI applications into production, not just prototyping in notebooksFluency in Dutch and English
Nice to have
Experience with agentic systems, multi-agent setups or MCPExperience with LLM observability and evaluation tooling such as Langfuse, LangSmith or RAGASExperience fine-tuning or self-hosting open-source models (LoRA, vLLM, Ollama)Experience with multimodal AI (documents, images, speech)Some frontend experience (TypeScript, React) to build usable interfaces
What you can expect
Challenging AI projects that go beyond experimentationPlenty of autonomy in a field that moves fast, with room to try new approachesBudget and time to keep up with the latest models and techniquesA small, close-knit team with direct influence on what gets builtHybrid working: part office, part remote
How it works
Kaleo works with multiple fast growing AI-native companies.
When you apply, we first get to know you and what you're looking for, and then match you with the company that fits you best.
