Python Full Stack AI Engineer - Pune, India

Role Overview

We are looking for a motivated Python Full Stack Engineer with hands-on exposure to Generative AI to join our growing engineering team. You'll build scalable web applications and integrate LLM-powered features into real products — working across the backend, frontend, and AI layers. This is a great role for an engineer with strong full stack fundamentals who has started working with LLMs and wants to go deeper. You'll get significant ownership, work directly with modern AI tooling, and grow alongside a fast-moving product.

Responsibilities

• Design, develop, and maintain backend applications and RESTful APIs using Python (FastAPI or Flask)
• Build responsive frontend interfaces using React.js
• Design and work with relational and NoSQL databases
• Integrate LLM APIs (OpenAI, Anthropic, Google Gemini) into product features
• Build and iterate on Retrieval-Augmented Generation (RAG) pipelines using frameworks like LangChain or LlamaIndex
• Apply prompt engineering, function calling, and structured outputs to make AI features reliable
• Integrate third-party APIs and external services
• Write clean, well-documented, and testable code
• Participate in code reviews, troubleshoot issues, and optimize performance
• Collaborate with product, design, and engineering teams to ship high-quality features.

Requirements

What We're Looking For

Must-have:

• 3+ years of professional experience in Python development
• Solid experience building REST APIs with FastAPI, Flask, or Django
• Working knowledge of React.js (or Angular) — comfortable building and modifying UI components
• Experience with SQL databases (PostgreSQL/MySQL); exposure to NoSQL (MongoDB, Redis) is a plus
• Hands-on experience integrating LLM APIs into an application — through work projects or substantial personal projects
• Understanding of prompt engineering and RAG concepts
• Strong debugging skills and software engineering fundamentals (Git, testing, code reviews)

Nice-to-have (not required):

• Experience with agent frameworks or multi-step LLM workflows
• Familiarity with vector databases (Pinecone, pgvector, Chroma, etc.)
• Exposure to Docker, CI/CD, or cloud platforms (AWS/GCP/Azure)
• Open-source contributions or a portfolio of AI-powered side projects