Software Engineer – AI/LLM & RAG Backend Developer

About the role

We are seeking a skilled Python developer to design and deliver AI‑driven backend solutions that combine Large Language Models with knowledge retrieval systems. You will work on cutting‑edge Retrieval‑Augmented Generation (RAG) pipelines and build scalable services for our products.

Key responsibilities

• Implement and maintain RAG pipelines using frameworks such as LangChain.
• Integrate LLM APIs (Azure OpenAI, Google Gemini) into applications.
• Set up and manage vector databases (Azure AI Search, Google Vector Search, PGVector, Pinecone, Milvus) for document storage and retrieval.
• Develop utilities for document preprocessing, chunking, and embedding generation.
• Build REST APIs with FastAPI or Flask to expose RAG/LLM workflows.
• Ensure backend services are reliable, scalable, and production‑ready.
• Create ETL scripts and data ingestion pipelines for structured and unstructured data.
• Monitor retrieval quality and optimise embeddings and reranking methods.

Required profile

• Bachelor’s degree in Computer Science or related field.
• 2–4 years of professional experience in Python development.

Required skills

• Python programming
• LangChain
• Azure OpenAI and Google Gemini APIs
• Vector databases (Azure AI Search, Google Vector Search, PGVector, Pinecone, Milvus)
• FastAPI or Flask
• REST API design
• ETL and data pipeline development
• Document preprocessing, chunking, and embedding generation