Open to opportunities

Patricia Ainembabazi

@patriciaainembabazi1

Message

Data Scientist using Python, SQL, and ML to build AI systems—seeking fully remote roles.

Kenya

Message

What I'm looking for

I’m seeking fully remote Data Scientist roles where I can build end-to-end Python/SQL AI systems, apply NLP (RAG/LLMs), and deliver production-ready applications that automate decisions.

I’m a Data Scientist with hands-on experience building end-to-end data and AI systems using Python, SQL, and modern machine learning. I use data wrangling, feature engineering, NLP, and applied machine learning to drive insight, automation, and intelligent decision-making.

In projects like Themis AI, I collected, cleaned, and structured large legal datasets, designed scalable PostgreSQL schemas, and developed RESTful APIs with Django—adding real-time transcription and automated case summarisation. I’ve also built an autonomous travel intelligence system using semantic search with pgvector and multi-agent reasoning, and delivered production-ready interfaces with Streamlit and FastAPI/Django REST Framework patterns, alongside dataset-focused work like StackOverﬂow feature engineering and IMDB 50K review sentiment classification.

Experience

Work history, roles, and key accomplishments

Data Scientist – Travel Planner

ThemisAgentic Travel Planner

Developed an autonomous travel intelligence system that generates personalised itineraries from large-scale web data. Implemented web-crawling and cleaning pipelines, embedding-based semantic search with pgvector, and a multi-agent reasoning approach, delivering a production-ready Streamlit interface.

Python SQL Data Crawling Text Cleaning Pgvector Embeddings RAG LLM Prompt Engineering Multi Agent Systems Streamlit

Data Scientist – Themis AI

Themis AI

Built an AI-driven judicial support platform by collecting, cleaning, and structuring large legal datasets with confidentiality in mind. Developed scalable PostgreSQL schemas and Django RESTful APIs, integrating real-time transcription with automated case summarisation and performing validation under high data volumes.

Python SQL Pandas PostgreSQL Django REST Framework REST APIs NLP Performance Testing

Sentiment Analysis Data Scientist

StackOverflow Colab IMDB

Built a sentiment analysis pipeline by preprocessing and analysing 50K IMDB movie reviews for classification. Conducted exploratory text analysis, trained Scikit-learn models, and evaluated performance using precision, recall, and F1-score.

Python scikit learn Text Analysis Classification Model Evaluation Precision Recall F1 Score

Feature Engineering Data Scientist

StackOverflow Dataset Analysis

Performed feature engineering on large categorical datasets to uncover trends and improve downstream model performance. Cleaned data, handled missing values, reduced high-cardinality features, and communicated results via visualisations while documenting workflows.

Python SQL Pandas Data Cleaning Feature Engineering Matplotlib SeaBorn Model Interpretability