Senior Applied AI Engineer

About the role

Azminds is seeking a Senior Applied AI Engineer to design and deliver production‑ready AI applications. The role focuses on building large language model (LLM) solutions, retrieval‑augmented generation (RAG) pipelines, and AI agents that integrate with databases, APIs and business tools.

Key responsibilities

• Design, develop, and deploy production‑grade LLM applications.
• Build RAG pipelines using embeddings, chunking, retrieval and reranking, and implement dense, sparse and hybrid search.
• Create AI agents that interact with databases, external APIs and internal tools.
• Develop scalable backend services with Python, FastAPI or Django.
• Enhance AI reliability through grounding, guardrails and systematic evaluation.
• Deploy, monitor and maintain AI applications on AWS.
• Lead technical planning, conduct code reviews, ensure testing and maintain documentation.
• Mentor junior engineers and champion engineering best practices.

Required profile

• 5+ years of professional software engineering experience.
• Strong expertise in Python and FastAPI/Django.
• Hands‑on experience building production RAG or AI‑agent applications.
• Deep understanding of embeddings, vector search and indexing.
• Experience with vector databases such as Qdrant, pgvector, Pinecone or Weaviate.
• Familiarity with LLM orchestration frameworks like LangGraph, LangChain or LlamaIndex.
• Knowledge of PostgreSQL/MySQL and REST API development.
• Proficiency with AWS, Git, Docker, testing and CI/CD pipelines.
• Solid grasp of API security, scalability and performance.
• Strong leadership, problem‑solving and communication abilities.
• Responsible use of AI development tools such as Claude Code, Codex or Cursor.

Required skills

• Python
• FastAPI
• Django
• AWS
• Git
• Docker
• CI/CD
• Testing frameworks
• PostgreSQL
• MySQL
• REST API development
• Embeddings and vector search
• Qdrant, pgvector, Pinecone, Weaviate
• LangGraph, LangChain, LlamaIndex
• LLM integration
• RAG pipelines
• AI agents