AI Engineer

Binaya Shrestha

AI Engineer focused on Large Language Models, Retrieval-Augmented Generation, and intelligent data-driven applications.

Building practical AI solutions with LLMs, vector search, document processing, and modern AI frameworks.

View Experience Connect on LinkedIn

Nepal

About

Binaya Shrestha is an AI Engineer specialising in Large Language Models and AI-powered applications. His work spans Retrieval-Augmented Generation, vector databases, semantic search, document processing, LLM evaluation, and prompt engineering. He builds scalable AI workflows using Python, LangChain, LlamaIndex, Amazon Bedrock, Pinecone, and Docker.

Most Recent Experience

AI Engineer

Leapfrog Technology, Inc.

Full-time
Apr 2022 – May 2024 · 2 yrs 2 mos Kathmandu, Nepal · Hybrid
  • Built and deployed Retrieval-Augmented Generation applications using LangChain, LlamaIndex, OpenAI, and Anthropic Claude.
  • Developed document-processing and semantic-search pipelines using Amazon Bedrock, Textract, S3, Pinecone, OpenSearch, and vector embeddings.
  • Evaluated LLM reliability, optimised system prompts, and explored open-source models (Llama 3, Mistral) and emerging AI platforms.
LangChain LlamaIndex RAG Amazon Bedrock

Core Expertise

AI & LLMs

Large Language Models RAG Prompt Engineering

Frameworks

LangChain LlamaIndex

Infrastructure

Vector Databases Amazon Bedrock Docker

Language

Python

Education

Kantipur Engineering College

Engineering College

Let's Connect

Interested in AI, LLMs, RAG, or intelligent software systems?
Connect with Binaya Shrestha on LinkedIn.

Connect on LinkedIn