Job Description:
As a Data Engineer, you will be responsible for designing and implementing backend services that integrate AI capabilities into various domains.
">
Key Responsibilities Include:
">
">
* Design, implement, and optimize pipelines to efficiently load documents, create embeddings, index vectors, cache, and tune performance.
">
* Integrate GenAI services with enterprise systems via REST APIs, webhooks, ensuring secure and scalable consumption of LLM capabilities.
">
* Develop evaluation frameworks (LLM as Judge, adversarial tests, prompt injection defence) for various use cases.
">
* Ensure robust observability of all GenAI components usage, latency, quality signals, drift, and feed insights into runbooks and continuous improvement loops.
">
">
Requirements:
">
A degree in computer science, engineering, mathematics, economics, or equivalent is required. You must also have experience in building and integrating data-driven backend services, including demonstrated hands-on experience with GenAI or LLM applications in production.
">
">
* Proficiency in Python and solid experience developing backend & API services.
">
* Proven achievements with LLM services, embeddings, and vector databases.
">
* Comfortable with GitLab CI/CD workflows and containerized deployments on Kubernetes.
">
* Security-minded and clear communicator able to explain complex GenAI behavior to non-experts.
">
* Excellent interpersonal skills, team spirit, and high degree of self-motivation.
">
* Highly effective verbal and written communication skills in English. A good knowledge of Luxembourgish, German, or French is considered an advantage.
">
"],