AI Engineer Intern

Overview

Role Overview:
We are seeking a highly motivated and technically strong AI Engineer Intern with hands-on experience in building Agentic AI systems, MCP-based workflows, and Retrieval-Augmented Generation (RAG) solutions. This role offers an opportunity to work closely with senior engineers and product leaders on real-world AI systems, contributing directly to production-grade applications.
The ideal candidate demonstrates strong Python fundamentals, practical exposure to LLM orchestration, and a clear understanding of how to design, implement, and optimize scalable RAG pipelines.

Key Responsibilities:

• Design, build, and optimize Agentic RAG systems using modern LLM frameworks.
• Implement Model Context Protocol (MCP) based integrations for structured AI interactions.
• Develop end-to-end RAG pipelines, including document ingestion, embedding, retrieval, and response generation.
• Write clean, modular, and production-ready Python code for AI workflows and services.
• Integrate vector databases and retrieval layers to improve accuracy, relevance, and latency.
• Collaborate with product, data, and engineering teams to translate requirements into AI-driven solutions.
• Test, evaluate, and iterate on prompt strategies, retrieval logic, and agent behaviors.
• Document system architecture, design decisions, and implementation details clearly.

Required Skills & Qualifications:

• Strong proficiency in Python with a solid understanding of software engineering fundamentals.
• Hands-on experience implementing Retrieval-Augmented Generation (RAG) systems.
• Practical exposure to Agentic AI frameworks and multi-step reasoning workflows.
• Experience working with LLMs, embeddings, and prompt engineering.
• Familiarity with vector databases (e.g., FAISS, Chroma, Pinecone, or equivalent).
• Understanding of MCP (Model Context Protocol) or similar structured AI orchestration patterns.
• Strong problem-solving skills and the ability to learn quickly in a fast-paced environment.
• API development and backend services (FastAPI, Flask, etc.).
• Experience with LangChain, LlamaIndex, or similar LLM orchestration frameworks.
• Familiarity with cloud or local LLM deployments.
• Prior internship, project, or open-source contributions in AI or ML systems.

What You Will Gain:

• Hands-on experience building real-world AI systems used in production.
• Exposure to advanced agentic architectures and RAG design patterns.
• Mentorship from experienced engineering leaders.
• Opportunity to convert the internship into a full-time role, based on performance.

Location & Work Model:

• Location: Bangalore (Work from Office)
• Role Type: Internship (Full-time)
• Department: Engineering