python backend

Cloudxtreme; Hyderabad, Chennai District, Bengaluru; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Cloudxtreme is seeking a skilled Python Developer to design and build intelligent, LLM-powered applications. You will craft scalable AI workflows and backend services that integrate Large Language Models with enterprise systems.

Key responsibilities include building LLM-driven applications, agent-based architectures, and RAG pipelines, with emphasis on prompt engineering and secure, performant deployments.

Qualifications

• Strong Python proficiency and modern language models experience.
• Hands-on with LangChain and LangGraph architectures.
• Experience building LLM-powered apps and RAG pipelines.
• Familiarity with prompt engineering, embeddings, and vector search.
• Experience with REST APIs and AI workflow orchestration.

Responsibilities

• Design and develop LLM-driven applications using Python.
• Build AI workflows, chains, and agent-based architectures with LangChain/LangGraph.
• Implement multi-step reasoning, stateful workflows, and tool-based agents.
• Integrate LLMs into backend systems and expose functionality via APIs.
• Practice security, data privacy, and responsible AI in production.

Skills

Python

LangChain

LangGraph

LLM apps

RAG pipelines

Prompt engineering

REST APIs

Vector search

LLM providers

AI orchestration

Git

Job description

Role & responsibilities

We are seeking a skilled Python Developer with strong experience in LangChain and/or LangGraphto design and build intelligent, LLM-powered applications. The role involves developing scalable AI workflows, agent-based systems, and backend services that integrate Large Language Models with enterprise systems.

Key Responsibilities

• Design and develop LLM-driven applicationsusing Python
• Build AI workflows, chains, and agent-based architectures using LangChainand LangGraph
• Implement multi-step reasoning, stateful workflows, and tool-based agents
• Integrate LLMs (OpenAI, Azure OpenAI, Anthropic, etc.) into backend systems
• Develop APIs and backend services to expose LLM functionality
• Implement prompt engineering, memory management, and context handling
• Optimize model performance, latency, and cost
• Integrate vector databases and retrieval mechanisms for RAG solutions
• Ensure security, data privacy, and responsible AI practices
• Debug, monitor, and enhance AI pipelines in production
• Collaborate with data scientists, product managers, and frontend teams

Required Skills & Qualifications

• Strong proficiency in Python
• Hands-on experience with LangChainand/or LangGraph
• Experience building LLM applications, agents, or RAG pipelines
• Understanding of prompt engineering, embeddings, and vector search
• Experience with LLM providers (OpenAI, Azure OpenAI, Anthropic, etc.)
• Knowledge of REST API development
• Familiarity with AI workflow orchestration and state management
• Strong debugging and problem-solving skills
• Experience using Git and collaborative development practices