Python Developer (RAG for AI Assistant)

Quick Facts

• Role: Python Developer (RAG for AI Assistant)

Description

You will develop backend services for an AI assistant in Python focused on RAG architecture. The work covers cleaning, indexing, and preparing data for language models, building context logic to send relevant information to the model, and integrating with Elasticsearch for high-precision retrieval. You will also run and monitor multi-DC services on Kubernetes with production-grade observability.

Responsibilities

• Develop Python backend services for a RAG-based AI assistant

• Design how data is cleaned, indexed, and prepared for language models

• Implement context-handling logic to reduce unnecessary tokens and improve relevance

• Integrate with Elasticsearch to obtain accurate search results

• Operate services in multi-DC Kubernetes environments

• Support development and deployment using GitLab and Argo CD on Linux

• Monitor service behavior using Prometheus, Grafana, Kibana, and OpenTelemetry

• Work with the team in a Scrum delivery rhythm

Requirements

• Strong Python programming skills

• Knowledge of RAG, especially embeddings, vector search, chunking, and prompt engineering

• Focus on efficiency, accuracy, latency, and compute utilization

• Interest in learning and applying new LLM methods in production

• Ability to explain your design in technical discussions and incorporate feedback

• Take ownership and deliver work with high quality

Benefits

• Work on RAG problems from a real product, not only demos

• See how your decisions impact answer quality

• Ability to test your ideas on a system that must work reliably in production

• Close collaboration with teams working on large-scale LLM, search, and data systems

• A team culture where technical arguments are taken seriously

• Access to work facilities in České Budějovice, Ostrava, Prague, or Zlín