Open to opportunities

Tayiba R

@tayibar

Message

Data Scientist with 4+ years building ML, NLP, and Generative AI solutions for fraud, risk, and RAG pipelines.

United States

Message

What I'm looking for

I’m looking for a role where I can build and deploy end-to-end ML, NLP, and Generative AI systems—especially fraud/risk and RAG/document intelligence—while collaborating across research and engineering to improve model quality and operational reliability.

I’m a Data Scientist focused on delivering end-to-end machine learning, NLP, and Generative AI systems that solve real business problems. I’ve worked across research, financial services, and enterprise environments, turning messy data into reliable models and production-ready pipelines.

At SCORE Lab, I investigate predictive modeling and classification pipelines using LangGraph, LangChain, and Large Language Models, and I’ve used Python-based statistical workflows (including hypothesis testing, correlation analysis, and regression modeling) to process 50K+ records. I also built Retrieval-Augmented Generation pipelines with LangChain and AWS Lambda to support document intelligence research and reduce manual extraction overhead.

Previously at Northern Trust, I designed credit risk analytics and fraud detection systems using LightGBM, PySpark, and feature engineering, as well as real-time AML pipelines with Apache Kafka, Structured Streaming, and Delta Lake. I deployed customer segmentation models on AWS SageMaker, automated portfolio analytics with Azure Data Factory and dbt, and engineered RAG architectures with Pinecone Vector Database and semantic search to cut analyst research time.

Earlier, as an Associate Data Scientist at Symtrax, I built ETL pipelines with Python, Apache Airflow, and AWS Glue, developed KPI dashboards with Pandas and SQL, and delivered interpretable churn forecasting models using scikit-learn with SHAP. I’m currently pursuing a Ph.D. in Information Science (Data Science), and I bring a research-minded, experiment-driven approach to every model I ship.

Experience

Work history, roles, and key accomplishments

Current

Data Scientist

Current

SCORE Lab

Aug 2024 - Present (1 year 11 months)

Worked on predictive modeling and classification pipelines using LangChain/LangGraph and large language models on research datasets. Conducted statistical analysis and implemented RAG pipelines for document intelligence using LangChain and AWS Lambda.

LangGraph Lang Chain Large Language Models Python MySQL Apache Airflow Pandas NumPy Tableau Hypothesis Testing Regression Modeling Clustering Retrieval Augmented Generation (RAG)Feature Engineering AWS Lambda Notion GitHub Document Intelligence

Data Scientist

Northern Trust

Aug 2023 - May 2024 (9 months)

Built credit risk analytics and fraud detection pipelines using machine learning and streaming technologies for financial datasets. Deployed customer segmentation and document-focused RAG architectures to reduce analyst and monitoring time.

LightGBM Pyspark Feature Engineering MLFlow Apache Kafka Delta Lake AWS Sagemaker XGBoost GitHub Azure Data Factory DBT PostgreSQL RAG Semantic Search Confluence Liquidity Prediction Market Forecasting Fraud Detection Credit Risk Analytics

Associate Data Scientist

Symtrax

Sep 2020 - Aug 2022 (1 year 11 months)

Built ETL pipelines and analytical reporting workflows using Python and cloud/data tools, including dashboards for business stakeholders. Developed predictive models for churn and applied NLP techniques with containerized classification scripts.