Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am an AI engineer and data scientist with 5+ years of experience spanning machine learning, NLP, and scalable AI systems. I focus on building and deploying LLM-powered applications and Retrieval-Augmented Generation (RAG) pipelines on AWS. I have a proven ability to develop end-to-end ML solutions that automate workflows, improve efficiency, and deliver measurable business impact.…

Parineeeta Borah

AI Engineer, Data Scientist, AI Developer, +2





I am an AI engineer and data scientist with 5+ years of experience spanning machine learning, NLP, and scalable AI systems. I focus on building and deploying LLM-powered applications and Retrieval-Augmented Generation (RAG) pipelines on AWS. I have a proven ability to develop end-to-end ML solutions that automate workflows, improve efficiency, and deliver measurable business impact.…

Available to hire

I am an AI engineer and data scientist with 5+ years of experience spanning machine learning, NLP, and scalable AI systems.

I focus on building and deploying LLM-powered applications and Retrieval-Augmented Generation (RAG) pipelines on AWS. I have a proven ability to develop end-to-end ML solutions that automate workflows, improve efficiency, and deliver measurable business impact.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

AI Developer and Data Specialist at Freedman International

February 1, 2025 - April 1, 2026

Designed, deployed, and productionized a scalable multilingual machine translation and back-translation pipeline using WordBee webhooks, AWS services, and Python workflows integrated with LLMs (GPT, LLaMA). Automated translation workflows and quality checks, reducing manual effort and operational costs by 30% while improving consistency across multilingual outputs.

Senior Analyst at Accenture

February 1, 2022 - May 31, 2023

Built and automated large-scale information extraction from enterprise systems by creating PyODBC-based pipelines for SQL data access and table generation, reducing manual data extraction time from hours to minutes.

Data Scientist at High Peak Software Ltd

September 1, 2018 - January 31, 2022

Built an Intelligent Document Processor to automate data collection, annotation, and synthetic sample generation. Integrated OpenCV preprocessing and trained a Faster R-CNN model to accurately detect and extract tabular structures from complex documents. Developed Flask-based APIs to serve AI models for real-time document parsing and analytics integration with client systems.