Twine
Twine

I'm Saima, a passionate Full Stack Developer, specializing in JavaScript, React.js, Next.js, Node.js, and GraphQL. I bring expertise in both frontend and backend development, creating intuitive, high-performance user interfaces…

SaimaRahman

I'm Saima, a passionate Full Stack Developer, specializing in JavaScript, React.js, Next.js, Node.js, and GraphQL. I bring expertise in both frontend and backend development, creating intuitive, high-performance user interfaces while building robust, scalable server-side applications. Having collaborated within agile teams, I prioritize clean, maintainable code and thrive in environments that embrace continuous integration and improvement. With a strong focus on problem-solving and adaptability, I’m currently…

Available to hire

I’m Saima, a passionate Full Stack Developer, specializing in JavaScript, React.js, Next.js, Node.js, and GraphQL. I bring expertise in both frontend and backend development, creating intuitive, high-performance user interfaces while building robust, scalable server-side applications. Having collaborated within agile teams, I prioritize clean, maintainable code and thrive in environments that embrace continuous integration and improvement. With a strong focus on problem-solving and adaptability, I’m currently seeking new opportunities where I can contribute my skills and grow alongside an innovative team.

See more

Language

English
Advanced

Work Experience

Add your work experience history here.

Education

Bachelors in Computer Science and IT at NED University of engg and tech
January 1, 2003 - December 31, 2006

Qualifications

Add your qualifications or awards here.

Industry Experience

Software & Internet, Energy & Utilities, Computers & Electronics
    paper RAG based Tenancy Chatbot
    A chat bot that answers questions related to the tenancy rules and regulations in Queensland using the "Retrieval Augmented Generation". The pdf document containing the rules and regulations regarding tenancy in QLD is uploaded to the server. Once uploaded the pdf is then broken down into chunks(Langchain), which are converted into vector representations(Langchain) and stored in a vector database (Pinecone). When users query the chatbot, the query is first converted to vector form and the relevant chunks of the documents addressing the query are retrieved from the vector database. The combined query, context and relevant documents are then used to generate a prompt(LLM). The newly generated prompt is then fed into the LLM to get the desired response.