CareerPlan

AI Application Engineer – AI Products (LLM & RAG) (m/f/d)

Berlin, Berlin, GermanyRemoteFull-time2026-10-23 → 2026-11-19
Hybrid

Core

Design and build user-facing AI applications and intelligent product features using LLMs and RAG for enterprise clients.

Role type

AI Application Engineer (LLM & RAG)

Builds

Enterprise assistants, AI copilots, semantic search platforms, intelligent automation systems, and scalable AI microservices.

Domain

Enterprise AI / Generative AI / Backend Development

Deliverable

production ML models

Required skills

Python, LLM APIs, RAG, vector databases, cloud platforms (AWS/Azure/GCP), backend frameworks, CI/CD, containerization

Preferred skills

LangChain, LlamaIndex, HuggingFace, AI observability, API design, microservices architecture

Technologies

Python, AWS, Azure, GCP, Docker, Kubernetes, LangChain, LlamaIndex, HuggingFace, Vector DBs

Responsibilities

Design and develop AI applications (assistants, copilots, search), build LLM-powered features with RAG, integrate LLM APIs and enterprise data, design scalable microservices, implement vector search and embeddings pipelines, prototype and evolve features to production, deploy to cloud with DevOps practices, collaborate with product managers and clients.

Seniority

Mid-Senior, hands-on IC