AI Intern (Internship cum Employment Program)

Role Overview

We’re looking for a curious, driven Python Intern to join our AI Solutions team. You’ll get your hands dirty building real products, work closely with senior engineers, and contribute to critical AI infra components. This isn’t a pretend internship—you will be part of our core team from day one.

Responsibilities

• Data Parsing & Cleaning: Write Python scripts to parse, transform, and wrangle structured and unstructured enterprise data for downstream AI consumption.
• RAG & Search Systems: Build end-to-end Retrieval-Augmented Generation (RAG) pipelines using vector databases (Pinecone, Qdrant, Chroma, pgvector) alongside traditional search engines (Elasticsearch, Solr) for hybrid search architectures.
• AI Agents & Multi-Agent Orchestration: Architect autonomous AI agents and complex multi-agent workflows capable of planning, dynamic tool-calling, state management, and multi-role collaboration.
• LLM Routing & Enterprise Cloud Orchestration: Build intelligent routing logic to dynamically direct queries across managed cloud platform suites—such as Azure AI Foundry, Amazon Bedrock, and Google Cloud Vertex AI—balancing cost, latency, and model availability.
• API Development & Microservices: Design and deploy fast, scalable REST/gRPC APIs using frameworks like FastAPI or Flask to seamlessly connect AI services with front-end applications.
• Containerization & Deployment: Containerize applications using Docker and Docker Compose to maintain consistent environment setups across local development, staging, and cloud production environments.
• Testing, Debugging & Evals: Write comprehensive unit tests for core backend services while establishing evaluation frameworks to benchmark agent performance and RAG retrieval accuracy.
• Documentation: Maintain clear, developer-friendly architectural diagrams and API documentation—leaving behind sustainable engineering practices, not spaghetti code.
• Exploration: Dive into emerging AI patterns, agentic frameworks, vector tech, and open-source libraries that move the needle for the product.

Requirements

• Practical experience integrating hyperscaler AI platforms (Azure AI Foundry, AWS Bedrock, GCP Vertex AI).
• Hands-on experience with modern agent and RAG frameworks (LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen).
• Familiarity with vector databases and hybrid search architectures (combining BM25 keyword search with dense vector embeddings).
• Proficiency with Docker, Docker Compose, and containerizing microservices for cloud deployment.
• Solid understanding of prompt engineering, structured outputs, and dynamic tool/function calling.
• Strong exposure to modern Python web frameworks (FastAPI, Flask, Django) and asynchronous programming.
• Strong Git practices and familiarity with CI/CD workflows for AI infrastructure.

Skills

• Python
• Flask
• Django
• FastAPI
• Docker