Open to opportunities

Natalie Marie Jaramillo

@nataliemariejaramill

Message

Data Scientist building responsible ML pipelines and actionable analytics dashboards.

United States

Message

What I'm looking for

I’m looking for a role where I can build end-to-end data/ML pipelines, create clear dashboards, and apply fairness-aware modeling. I want to collaborate with researchers or product teams to turn analytics into real-world impact.

I’m a Data Scientist who loves turning messy, high-volume data into trustworthy models and decisions. I build end-to-end pipelines, benchmark approaches, and ship analytics that people can actually use.

Currently, I’m a Data Scientist Consultant (Contract) with The Nature Conservancy, where I led a student team collaborating with academic researchers to optimize geospatial ML models predicting Snow Cover Duration and Snow Water Equivalent. By tuning and benchmarking Random Forest, XGBoost, and LightGBM, I selected an Extra Trees model and achieved strong performance with a 0.965 test R and only a 0.03 train-test R gap.

Earlier, as a Data Analyst Intern (April 2026 – Present) at IDX Exchange, I’m building a Python-based end-to-end MLS data pipeline extracting, processing, and analyzing 1M+ California residential transactions from the CoreLogic Trestle API. I also develop interactive Tableau dashboards for market and competitive intelligence, including zip code heat maps, agent/brokerage performance rankings, and monthly pricing trend visualizations.

I also bring applied NLP and research rigor to my work, including an Applied Data Scientist (Contract) engagement at Stride where we built an NLP-based analytics framework analyzing 1.6M+ Discord messages to model user behavior and community well-being. In research, I’m designing an AI-assisted qualitative coding pipeline to analyze 20+ interviews and validating thematic segments from 70 interview transcripts, and I prioritize fairness, clarity, and reproducibility in every project I touch.

Experience

Work history, roles, and key accomplishments

Current

Data Analyst Intern

Current

IDX Exchange

Apr 2026 - Present (2 months)

Built an end-to-end MLS data pipeline in Python to extract, process, and analyze 1M+ California residential real estate transactions from the CoreLogic Trestle API across 27 months. Developed interactive Tableau dashboards for market and competitive intelligence, including zip code heat maps, agent/brokerage rankings, and monthly pricing trends.

Python Data Pipelines CoreLogic Trestle API Data Analysis Tableau Data Visualization Market Intelligence

Current

Data Scientist Consultant

Current

The Nature Conservancy

Jan 2026 - Present (5 months)

Led a student team collaborating with academic researchers to optimize geospatial ML models predicting snow cover duration and snow water equivalent from forest-structure features. Tuned and benchmarked Random Forest, XGBoost, and LightGBM, selecting an Extra Trees model with 0.965 test R and a 0.03 train-test R gap.

Feature Engineering Random Forest Extra Trees XGBoost LightGBM Hyperparameter Tuning Benchmarking Model Evaluation

Current

Undergraduate Research Assistant

Current

Center for Research on Expanding Educational Opportunity

Sep 2025 - Present (9 months)

Collaborate with UC Berkeley faculty to study Afro-descendant educators in Latin America by analyzing 20+ interviews and instructional materials to identify instructional patterns and themes. Designed an AI-assisted qualitative coding pipeline using LLM prompt optimization and validation of thematic segments from 70 interview transcripts.

Thematic Analysis LLM Prompt Engineering Research Collaboration Data Validation

Applied Data Scientist

Stride

Sep 2025 - Dec 2025 (3 months)

Collaborated with a student team to build an NLP-based analytics framework analyzing 1.6M+ messages from five Discord communities to model user behavior and community well-being. Created data pipelines and visual analytics that surfaced sentiment and community health trends for use in an interactive dashboard for moderators and client teams.

NLP Sentiment Analysis User Behavior Analytics Predictive Analytics Data Pipelines Data Visualization Python Dashboarding

Education

Degrees, certifications, and relevant coursework

University of California, Berkeley

Bachelor of Arts, Data Science

Activities and societies: Minor in Education; relevant coursework includes Data Structures and Algorithms, Probability for Data Science, and Computational Structures in Data Science.

Pursuing a B.A. in Data Science with a minor in Education at UC Berkeley, expected to graduate in May 2027.