AI - Intern

RRD; Chennai; On-site; INR 152,000 - 182,000; Part time

Benefits offered by this job

Stipend 15K INR/month

Office-based internship

Job summary

RRD invites an AI Intern to join our office-based team in Chennai. You will design and deploy intelligent, multimodal AI systems, integrating LLMs and RAG pipelines, and build scalable APIs using Flask or FastAPI. Collaboration with frontend/backend teams is key.

The role covers diffusion-based generation, vector databases, and workflow automation, with emphasis on prompt engineering and tooling integration. 3-month internship with a 15K INR monthly stipend.

Qualifications

• Proficient in Python and JavaScript.
• Experience with Flask, FastAPI, and Node.js.
• Hands-on experience with LLMs (Gemini, Claude, GPT, Hugging Face Transformers) including model fine-tuning.
• Understanding of autonomous agent design, decision-making loops, and task chaining.
• Experience building end-to-end Retrieval-Augmented Generation (RAG) systems using LangChain or LangGraph.
• Familiarity with vector databases such as Pinecone, FAISS, or Chroma.
• Knowledge of ComfyUI, Stable Diffusion, Runway, or Midjourney.
• Proficiency in workflow automation using n8n.
• Experience designing and refining structured prompts for LLM accuracy and creativity.
• Strong knowledge of API integration across AI tools and frameworks.

Responsibilities

• Design, develop, and deploy intelligent Agentic AI systems and RAG pipelines.
• Integrate, fine-tune, and optimize LLMs for text and multimodal applications.
• Build workflow automations using n8n and AI pipelines in ComfyUI.
• Implement diffusion-based image and video generation using Runway, Midjourney, and Stable Diffusion.
• Develop and maintain API services using Flask and FastAPI.
• Manage and query vector databases and embeddings to support retrieval-augmented AI systems.
• Work on prompt engineering for LLM task optimization and contextual understanding.
• Collaborate with frontend and backend teams for seamless API integration and AI model deployment.
• Utilize code interpreters for automation and dynamic code execution.
• Maintain repositories, documentation, and collaboration using Git and GitHub.
• Ideate and develop new AI-powered tools leveraging existing AI platforms.

Skills

Python

JavaScript

Flask

FastAPI

Node.js

LLMs

RAG pipelines

n8n

ComfyUI

API deployment

Git/GitHub

Tools

LangChain

LangGraph

Pinecone

FAISS

Chroma

ComfyUI

Runway

Midjourney

n8n

GitHub

Job description

AI - Intern

Work Mode: Office

Stipend: 15K Per month

Duration : 3 Months

JOB DESCRIPTION

Knowledge in building intelligent, automated, and multimodal AI systems.Strong experience with Python, JavaScript, LLMs (Gemini, Claude, GPT), RAG architectures, Agentic AI, andvisual diffusion models. Integrating cutting-edge AI tools, creating automation workflows with n8n and ComfyUI, fine-tuning and deploying models, and developing scalable APIs using Flask or FastAPI.

Responsibilities

• Design, develop, and deploy intelligent Agentic AI systems and RAG pipelines.
• Integrate, fine-tune, and optimize LLMs (Gemini, Claude, GPT, Hugging Face Transformers) for text and multimodal applications.
• Build workflow automations using n8n and AI pipelines in ComfyUI.
• Implement diffusion-based image and video generation using tools such as Runway, Midjourney, and Stable Diffusion.
• Develop and maintain API services using Flask and FastAPI.
• Manage and query vector databases (Pinecone, FAISS, Chroma) and embeddings to support retrieval-augmented AI systems.
• Work on prompt engineering for LLM task optimization and contextual understanding.
• Collaborate with frontend and backend teams for seamless API integration and AI model deployment.
• Utilize code interpreters for automation and dynamic code execution.
• Maintain repositories, documentation, and collaboration using Git and GitHub.
• Ideate and develop new AI-powered tools or solutions by leveraging existing AI platforms and technologies.

Required Skills and Experience

• Proficient in Python and JavaScript.
• Experience with Flask, FastAPI, and Node.js.
• Hands-on experience with LLMs (Gemini, Claude, GPT, Hugging Face Transformers)including model fine-tuning.
• Understanding of autonomous agent design, decision-making loops, and task chaining.
• Experience building end-to-end Retrieval-Augmented Generation (RAG) systems using LangChain or LangGraph.
• Familiarity with vector databases such as Pinecone, FAISS, or Chroma.
• Knowledge of ComfyUI, Stable Diffusion, Runway, or Midjourney.
• Proficiency in workflow automation using n8n.
• Experience designing and refining structured prompts for LLM accuracy and creativity.
• Strong knowledge of API integration across AI tools and frameworks.