AI Engineer (Intern)

INPRO; Bengaluru; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

INPRO in Bengaluru is seeking an ML engineer to build robust AI pipelines that convert unstructured industrial documents into structured data and enhance automation, accuracy, and scalability across workflows.

You will develop and optimize LLM, OCR, and semantic search systems with retraining, collaborating with cross-functional teams to deploy production-ready models. Proficiency in Python, PyTorch or TensorFlow, LangChain/LlamaIndex is required.

Qualifications

• BE-IT/Computer/Computer Science and Design/Computer Science BTECH-CSE/IT BSC-Computer Science/IT BCA-IT/Computer MCA-IT/Computer Science MSC-IT/Computer ME-Computer BCCA-Computer BBA(CA)-Computer MBA-IT MCM-Computer BCS-Bachelor of Computer Science
• Our placement training students get interview calls weekly with resume prep, mock interviews and unlimited calls until placed.

Responsibilities

• Build robust AI pipelines converting unstructured industrial documents into structured data while improving accuracy, automation efficiency, and model scalability across workflows.
• Develop and optimize LLM, OCR, and semantic search systems with feedback-driven retraining to enhance performance across diverse real-world industrial datasets.
• Collaborate with product, engineering, and data teams to deploy production-ready models powering critical industrial workflows.
• Maintain clean coding habits, Git/GitHub workflow, and design modular, production-ready ML systems.

Skills

Python

ML fundamentals

PyTorch

TensorFlow

LLM frameworks

LangChain

LlamaIndex

Embeddings

Semantic search

Git/GitHub

Education

IT/CS/Engineering degree as listed

Tools

LangChain

LlamaIndex

PaddleOCR

LayoutLM

Donut

AWS

APIs

Graph databases

Job description

• Build robust AI pipelines converting unstructured industrial documents into structured data while improving accuracy,
• automation efficiency, and model scalability across workflows.
• Develop and optimize LLM, OCR, and semantic search systems with feedback-driven retraining to enhance performance across
• diverse real-world industrial datasets.
• Collaborate with product, engineering, and data teams to deploy production-ready models powering critical industrial
• Strong Python and ML fundamentals (PyTorch or TensorFlow).
• Hands-on experience with LLM frameworks (LangChain, LlamaIndex, etc.).
• Familiarity with Document AI / OCR models (PaddleOCR, LayoutLM, Donut).
• Solid understanding of embeddings, semantic search, and entity linking.
• Clean coding habits, Git/GitHub workflow, and ability to design modular,
• production-ready ML systems.
• Good Knowledge Of Embeddings, Semantic Search, RAG
• Good Knowledge Of LLMs, RAG (Retrieval Augmented Generation), semantic search, OCR models, AWS, APIs, graph databases, and GraphRAG.

Qualifications

BE-IT/Computer/Computer Science and Design/Computer Science BTECH-CSE/IT BSC-Computer Science/IT BCA-IT/Computer MCA-IT/Computer Science MSC-IT/Computer ME-Computer BCCA-Computer BBA(CA)-Computer MBA-IT MCM-Computer BCS-Bachelor of Computer Science

Our placement training students get interview calls like this one every week — with resume prep, mock interviews and unlimited calls until placed.