Question 1

What is Aryan Gupta's specialisation as an AI Engineer?

Accepted Answer

Aryan Gupta specialises in Agentic AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) pipelines, and production AI systems built with LangChain, LangGraph, vector databases, and deployed on AWS.

Question 2

What RAG and LLM projects has Aryan Gupta worked on?

Accepted Answer

Aryan has built a production Compliance RAG System using hybrid search (Qdrant + BM25), cross-encoder re-ranking, LangChain, and FastAPI deployed on AWS EC2 with Docker and CI/CD. He also builds credit risk ML pipelines and forecasting dashboards. See aryangupta.work for details.

Question 3

What tech stack does Aryan Gupta use?

Accepted Answer

Aryan uses LangChain, LangGraph, OpenAI APIs, Qdrant, FAISS, FastAPI, Pydantic, Docker, GitHub Actions CI/CD, and AWS cloud services (EC2, S3, Lambda, SageMaker) for building and deploying AI systems.

Question 4

Where is Aryan Gupta based?

Accepted Answer

Aryan Gupta is based in New Delhi, India, and is open to remote and hybrid AI/ML engineering roles globally.

Question 5

How can I contact Aryan Gupta for AI engineering work?

Accepted Answer

You can reach Aryan at aryangupta.7263@gmail.com, via LinkedIn at linkedin.com/in/aryangupta7263, or through the contact form at aryangupta.work.