AI Intern

InfraCents Pvt. Ltd.; India; Remote; INR 167,000 - 279,000; Full time

Benefits offered by this job

Hugging Face exposure

NLP/PyTorch projects

MCP familiarity

Job summary

InfraCents Pvt. Ltd. is seeking an AI Intern to help build generative AI features for client and internal products, working with an AI engineer as a mentor.

You will prototype, test and measure LLM applications such as retrieval-augmented assistants, document processing and simple agents. The role suits someone who has built with LLM APIs, understands their limits, and wants to learn how to make AI features reliable enough for production.

Qualifications

• Good Python skills and a basic understanding of machine learning concepts.
• Has built at least one project using an LLM API, such as a chatbot, RAG app or agent.
• Strong communication and ability to document experiments clearly.
• Curiosity about the fast-moving AI ecosystem.

Responsibilities

• Prototype LLM features using prompting, retrieval (RAG) and tool calling.
• Prepare, clean and chunk documents for retrieval pipelines.
• Build small APIs and demo interfaces for AI features.
• Create evaluation datasets and measure accuracy, latency and cost.
• Document prompts, experiments and results so others can reproduce them.

Skills

Python

ML concepts

LLM API project

Critical thinking

Communication

Education

CS/IT/Engineering student

Tools

Python

Jupyter

pandas

NumPy

Anthropic Claude

OpenAI

Google Gemini

LangChain

LangGraph

LlamaIndex

Embeddings

pgvector

Chroma

Qdrant

Ragas

promptfoo

FastAPI

Streamlit

Gradio

Git

Docker basics

Job description

About InfraCents

InfraCents is a software engineering company. We design and build software products, run the cloud platforms they live on, build AI systems and data pipelines, and keep all of it secure, reliable and cost-efficient in production. Our engineers work directly with clients, own outcomes end to end and are trusted with real production systems. We value clear thinking, honest communication and work that still holds up a year after it ships.

Role Overview

The AI Intern will help build generative AI features for client and internal products, working with an AI engineer as a mentor. You will prototype, test and measure LLM applications such as retrieval-augmented assistants, document processing and simple agents.

The role suits someone who has built with LLM APIs, understands their limits, and wants to learn how to make AI features reliable enough for production.

Key Responsibilities: Build & Experiment

• Prototype LLM features using prompting, retrieval (RAG) and tool calling.
• Prepare, clean and chunk documents for retrieval pipelines.
• Build small APIs and demo interfaces for AI features.

Key Responsibilities: Evaluate & Document

• Create evaluation datasets and measure accuracy, hallucination rate, latency and cost.
• Compare models and approaches and summarise findings clearly.
• Document prompts, experiments and results so others can reproduce them.

Who We're Looking For

• Fundamentals: Good Python skills and a basic understanding of machine learning concepts.
• Hands-on: Has built at least one project using an LLM API, such as a chatbot, RAG app or agent.
• Critical thinking: Questions model output instead of trusting it, and measures results.
• Communication: Writes clear notes and explains experiments simply.
• Passion: Keeps up with the fast-moving AI ecosystem.

Technical Expertise Required

• Languages & Notebooks: Python, Jupyter, pandas, NumPy
• LLM APIs: Anthropic Claude, OpenAI, Google Gemini
• Frameworks: LangChain / LangGraph, LlamaIndex
• Retrieval: Embeddings, pgvector, Chroma, Qdrant
• Evaluation: Ragas, promptfoo
• Apps & Tools: FastAPI, Streamlit / Gradio, Git, Docker basics

Nice to Have

• Exposure to Hugging Face models or running open-weight models locally (Ollama).
• Coursework or projects in NLP or deep learning (PyTorch).
• Familiarity with the Model Context Protocol (MCP).

Qualifications

• Experience: 0-1 years, including internships and substantial personal projects.
• Education: Final-year student or recent graduate in Computer Science, IT, Engineering or a related field, or equivalent self-taught experience with a portfolio to show for it.