? WE ARE HIRING | AI Backend Engineer

We are looking for talented AI Backend Engineers with strong expertise in Python backend development and hands-on experience building AI-powered applications using Generative AI, LLMs, and RAG architectures.

? Location: Remote

? Experience: 3–5 Years

? Work Mode: Work From Home

? Key Responsibilities

- Design, develop, and maintain scalable backend applications using Python.
- Build RESTful APIs and microservices using FastAPI, Flask, or Django.
- Integrate Large Language Models (LLMs) such as OpenAI, Azure OpenAI, Claude, Gemini, and Llama.
- Develop and implement Retrieval-Augmented Generation (RAG) pipelines.
- Build AI-powered applications using LangChain, LangGraph, or similar frameworks.
- Implement prompt engineering, embeddings, semantic search, and vector database integrations.
- Develop AI agent workflows, tool calling, and function calling capabilities.
- Integrate vector databases such as Pinecone, FAISS, ChromaDB, Weaviate, and Qdrant.
- Work with SQL/NoSQL databases and asynchronous processing.




- Optimize backend performance, API response times, and application scalability.
- Deploy and maintain AI applications using Docker, Kubernetes, and cloud platforms.

? Mandatory Skills
- Strong programming experience in Python.
- Hands-on experience with FastAPI / Flask / Django.
- Solid knowledge of REST APIs and backend development.
- Experience integrating OpenAI, Azure OpenAI, Claude, or other LLM APIs.
- Understanding of Generative AI and LLM concepts.
- Hands-on experience with RAG architecture and embeddings.
- Knowledge of vector databases.
- Experience with SQL / NoSQL databases.
- Familiarity with Git, Docker, and cloud technologies.

? Good to Have
- LangChain / LangGraph / CrewAI.
- Agentic AI and MCP (Model Context Protocol).
- Kafka / RabbitMQ / Redis.
- AWS / Azure / GCP.
- Kubernetes and CI/CD pipelines.
- Production deployment and monitoring of AI applications.

📌 AI Backend Engineer (India)
🏢 Aventra.AI
📍 India