AI Python Ful Satck Developer (LLM)

AI Python Full Stack

Experience: 3 6 Years

Location: Bangalore

Positions: 2

Employment Type: Full-time

About The Role

We are looking for an AI Application Engineer to build and integrate production-ready AI applications using LLMs, AI agents, MCP, voice integrations, workflow automation, and cloud-native technologies. This role focuses on integrating existing AI models and services rather than training foundation models.

Key Responsibilities

• Build scalable AI-powered applications using Python/Node.js and React.
• Integrate OpenAI, Gemini, AWS, and other LLM services.
• Develop AI agents, tool calling, prompt engineering, structured outputs, and streaming responses.
• Build and consume MCP servers and clients.
• Develop modern frontend applications using React, TypeScript, Hooks, and state management.
• Build backend APIs using FastAPI/Django/Flask or Node.js.
• Implement event-driven workflows and automation.
• Deploy applications using AWS, Docker, Kubernetes/serverless, CI/CD, and IaC.
• Work with PostgreSQL and MongoDB.
• Optimize AI applications for cost, latency, reliability, and performance.

Must-Have Skills

• Strong Python or Node.js development experience.
• Strong React + TypeScript experience.
• Hands-on experience with LLM APIs such as OpenAI, Gemini, or AWS.
• Experience with MCP (Model Context Protocol).
• Experience with Docker, AWS, CI/CD, and cloud-native development.
• Strong knowledge of PostgreSQL and MongoDB.
• Understanding of APIs, asynchronous programming, and production application development.

Good to Have

• Voice AI: Speech-to-Text / Text-to-Speech.
• LLM observability and evaluation.
• RAG, vector databases, and AI agent frameworks.
• Cost and latency optimization using caching, model routing, batching, and prompt compression.
• Experience with event-driven architectures and real-time services.