AI Solutions Backend Engineer (RAG & LLM Systems)

YOUR MISSION

Build and orchestrate AI workloads using Azure Foundry

Design and implement RAG systems and hybrid retrieval pipelines

Develop backend services with Django and FastAPI

Integrate LLM APIs (OpenAI, Anthropic, Mistral, Azure OpenAI)

Implement prompt engineering and agent workflows using LangChain, LangGraph, and LlamaIndex

Manage vector databases (Pinecone, FAISS, Weaviate, pgvector) for embedding search

Design indexing, data pipelines, and retrieval layers with Azure AI Search and Blob Storage

YOUR EXPERIENCE & TALENTS

Strong hands-on expertise in RAG architecture, LLM tooling, and AI orchestration

Deep knowledge of LangChain, LangGraph, LlamaIndex, and agentic frameworks

Proficiency with Django, FastAPI, and modern backend development

Experience with vector DBs and embedding-based retrieval

Ability to design scalable pipelines, optimize prompts, and build production-ready AI workflows

Familiarity with Azure ecosystem, data indexing, and search technologies

BENEFITS OFFERED BY OUR CLIENT

Work with top-tier talent in a collaborative, high-performing team

Grow through cutting-edge technologies, continuous learning, and certification opportunities

Thrive in a global, diverse culture while contributing to exciting, cross-industry projects

Enjoy 50+ tailored benefits and a flexible hybrid working model

Balance work and life in a culture that supports your personal and professional development