AI Data Engineering

Avenga is an international engineering firm helping businesses operate with AI at the core. With 6,000+ experts worldwide, we combine engineering expertise with AI-native thinking to turn ambitious ideas into real-world impact across industries, technologies, and markets. At the core of the role The candidate will work on the core engine behind a production AI assistant: an agentic AI system focused on retrieval, LLM orchestration, and answer quality. The product is designed to evolve AI-powered customer support from simply answering questions to executing customer requests. Rather than only providing information (e.g., explaining a bill), the assistant is built to safely perform actions such as placing orders or activating services while operating within the rules and constraints of a regulated telecom environment. We care far more about how candidates think about retrieval quality than which specific libraries or frameworks they've used. The technology stack can be learned; strong engineering judgment and problem-solving are what we're looking for. Core skills you’ll bring 3+ years Proficiency in building production Python services (async, API design) Experience designing and building REST APIs (and consuming them); comfortable with request/response modelling, auth, and versioning Hands-on experience building RAG / retrieval-augmented generation systems: not just calling an LLM API, but chunking, retrieval, and grounding answers in sources (preferably LangChain, Langfuse, Llamaindex, FastAPI, Pydantic) Experience vector database (e.g. Milvus, Pinecone, Weaviate, Qdrant, pgvector) and an understanding of embeddings and similarity search A habit of evaluating and validating LLM output quality. (Azure OpenAI) RAG pipeline methodology and process Data ingestion, Chunking/Similarity search (for structured and unstructured data). CI/CD pipeline expertise (preferably Github) Familiarity with Infra as Code (Teraform)and API gateway Cloud expertise (preferably AWS) Writes automated tests as a matter of habit unit and integration testing with pytest (mocking, fixtures)AG/LLM open source, or published eval work, a GitHub profile showing real projects is a plus People are at the core of Avenga. We provide equal opportunities regardless of race, ethnicity, gender identity, sexual orientation, disability, age, religion, or any other characteristic. We are committed to a respectful environment where everyone can be themselves, share their ideas, and feel that they belong.