For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

Invite to Job
Vida Ahmadi

Vida Ahmadi

Machine Learning Engineer - Natural Language Processing

ITALY flag
torino, Italy
$20.00/hrIntermediateOther

Key Skills

Software

Other

Top Subject Matter

No subject matter listed

Top Data Types

TextText

Top Label Types

Entity Ner Classification

Freelancer Overview

I have a Master’s degree in Data Science & Engineering and more than four years of experience in machine learning, deep learning and natural‑language processing. I have built and fine‑tuned transformer‑based models using Python, PyTorch and TensorFlow, and I regularly use libraries such as scikit‑learn, Pandas and Hugging Face. My professional background as a Python developer and Android developer, coupled with hands‑on experience in big‑data tools like Spark and Hadoop, has given me a solid foundation in software engineering and data management. I am fluent in English. In my research and project work I have developed end‑to‑end NLP pipelines that include data preparation, annotation, model training and evaluation. I have experience balancing class distributions, implementing data‑augmentation techniques and designing multi‑task learning architectures. I pride myself on attention to detail, strong problem‑solving skills and the ability to quickly learn new labeling guidelines. I enjoy collaborating with teams to produce high‑quality training data that improves model performance.

IntermediateEnglishPersian Farsi

Labeling Experience

Clinical Text Re-Annotation & Entity Alignment (Academic Project)

OtherTextEntity Ner Classification
As part of my Master's thesis on clinical NLP, I experimented with re-annotating portions of the i2b2 2014 medical dataset using MetaMap for automated medical concept extraction. Tasks performed: Ran MetaMap to extract UMLS concepts from clinical narratives Compared extracted entities with existing gold annotations Adjusted entity spans to align with token-level BIO format Cleaned text while preserving character offsets Reviewed boundary mismatches between automated and original annotations Conducted small-scale manual validation to verify alignment accuracy Project Scope: Academic-scale experimentation (subset of clinical narratives) Quality Measures: Manual inspection of entity span mismatches Offset validation to prevent annotation drift Verification of medical concept normalization

As part of my Master's thesis on clinical NLP, I experimented with re-annotating portions of the i2b2 2014 medical dataset using MetaMap for automated medical concept extraction. Tasks performed: Ran MetaMap to extract UMLS concepts from clinical narratives Compared extracted entities with existing gold annotations Adjusted entity spans to align with token-level BIO format Cleaned text while preserving character offsets Reviewed boundary mismatches between automated and original annotations Conducted small-scale manual validation to verify alignment accuracy Project Scope: Academic-scale experimentation (subset of clinical narratives) Quality Measures: Manual inspection of entity span mismatches Offset validation to prevent annotation drift Verification of medical concept normalization

2024 - 2024

Education

P

Polytechnic University of Turin

Master of Technology, Data Science and Engineering

Master of Technology
2022 - 2025
K

Kurdistan University

Bachelor of Technology, Information Technology

Bachelor of Technology
2010 - 2014

Work History

Z

Zharfa Company

Python Developer

Kurdistan
2019 - 2021
B

Banta Pardaz Pooyan

Android Developer

Kurdistan
2017 - 2019