AI Data Engineer

This is a fully remote position, open to applicants in Czechia.

📋 Description

• Contribute to the fundamental engine that powers a production AI assistant

• Emphasize retrieval, LLM orchestration, and the quality of answers

• Advance AI-driven customer support from merely responding to inquiries to fulfilling requests

• Execute actions such as placing orders or activating services safely within a regulated telecom environment

⛳️ Requirements

• Over 3 years of experience

• Expertise in developing production-grade Python services (asynchronous programming, API design)

• Background in designing and constructing REST APIs (as well as utilizing them)

• Practical experience in building RAG / retrieval-augmented generation systems (ideally with LangChain, Langfuse, Llamaindex, FastAPI, Pydantic)

• Familiarity with vector databases (such as Milvus, Pinecone, Weaviate, Qdrant, pgvector) and a solid understanding of embeddings and similarity searches

• Skills in assessing and validating the quality of LLM outputs (Azure OpenAI)

• Experience in data ingestion and chunking/similarity searching for both structured and unstructured data

• Proficient in CI/CD pipeline management (preferably with GitHub)

• Knowledge of Infrastructure as Code (Terraform) and API gateways

• Cloud experience (preferably with AWS)

• Regularly writes automated tests (unit and integration testing using pytest)

• Contributions to AG/LLM open source projects or published evaluation work, along with a GitHub profile showcasing real projects, is a beneficial addition

🏝️ Benefits

• Commitment to equal opportunities in recruitment and career advancement

• Promoting a work culture that supports a diverse community