Isabel is available for hire
Hire IsabelIsabel Escobar Rivas
Verified Expert in Engineering
Data Science and Machine Learning Developer
San Diego, United States
Toptal member since July 20, 2026
Bio
Across technology and customer experience analytics, Isabel has spent eight years building NLP and machine learning solutions for companies including ServiceNow, Airbnb, and Meta. Her toolkit centers on Python, SQL, and Tableau. While at ServiceNow, Isabel built self-service CX analytics platforms integrating NPS, CSAT, and product adoption data.
Portfolio
Google Fiber
SQL, Python, Pandas, Looker, BigQuery
Meta
Python, SQL, Tableau
Airbnb
Natural Language Processing (NLP), Large Language Models (LLMs), Python, Pandas...
Experience
- SQL - 10 years
- Tableau - 8 years
- Pandas - 8 years
- Python - 8 years
- Amazon EC2 - 3 years
- Large Language Models (LLMs) - 3 years
- Retrieval-augmented Generation (RAG) - 2 years
- NumPy - 1 year
Preferred Environment
Looker, BigQuery, Tableau, Amazon EC2, Docker Compose, GitHub Actions
The most amazing...
...AI platform I've architected is StyLens, a four-agent system with patent pending and a $750,000 pre-seed raise in progress.
Work Experience
Data Science and Analytics Engineer
2026 - PRESENT
Google Fiber
- Built SQL pipelines with temporary tables and CTEs to integrate multi-source operational, behavioral, and transactional data. Used Python (Pandas) for quantitative analysis and data transformation, creating unified views of performance drivers.
- Designed hypothesis-driven experimental loops using Python and SQL for quantitative analysis to validate capacity decisions.
- Developed PLX, Looker, and BigQuery dashboards tracking KPIs and communicating system behavior findings through data visualization reports to both technical and executive audiences. Utilized AI tools to accelerate analysis and reporting.
- Partnered cross-functionally with revenue, engineering, and operations to translate ambiguous data requirements into structured research problems and actionable insights.
Technologies: SQL, Python, Pandas, Looker, BigQuery
Data Analytics Engineer
2025 - 2026
Meta
- Maintained and optimized Python and SQL pipelines ingesting contact center operational data across call volume, agent performance, issue type, managing partner, vendor, location, and language dimensions.
- Built and maintained Tableau dashboards tracking key CX KPIs, delivering data visualizations and reports to leadership and analyst audiences.
- Conducted quantitative analysis on contact center performance trends to surface actionable CX insights for operational decision-making.
Technologies: Python, SQL, Tableau
LLM Data Engineer
2024 - 2025
Airbnb
- Applied NLP and LLM pipelines to classify, summarize, and extract structured insights from large-scale unstructured text (regulatory documents, stakeholder feedback) using Python (Pandas, scikit-learn) and SQL.
- Built ETL pipelines integrating behavioral and operational data sources to deliver decision-ready reports and data visualizations. Utilized AI tools to accelerate data processing and insight generation. Surfaced cross-functional insights.
- Designed evaluation rubrics and selection criteria for LLM providers across accuracy, latency, and cost. Defined governance standards for enterprise deployment.
Technologies: Natural Language Processing (NLP), Large Language Models (LLMs), Python, Pandas, Scikit-learn, SQL
AI Engineering Lead, Product Owner
2023 - 2024
2Xplore Immigration (LegalLanguageModels)
- Designed and implemented NLP pipelines and evaluation frameworks measuring reasoning accuracy, hallucination risk, and retrieval groundedness across agent workflows using Python. Applied quantitative analysis to benchmark model outputs.
- Built a production multi-agent system with RAG-based semantic retrieval, document classification, and confidence scoring to determine automation vs escalation routing across real paralegal workflows.
- Surfaced and prioritized system failure modes using targeted test datasets and experimental protocols. Utilized AI tools throughout development to accelerate iteration. Led V1-to-V2 redesign to enterprise multi-tenant architecture.
- Produced detailed SQL-backed reports on system performance for stakeholder review.
Technologies: Natural Language Processing (NLP), Python, Retrieval-augmented Generation (RAG), .NET, SQL
Customer Insights, Business Analytics Lead
2018 - 2022
ServiceNow
- Built self-service CX analytics platforms integrating NPS, CSAT, and product adoption data, producing Tableau data visualizations, KPI dashboards, and executive reports in Python and R for cross-functional stakeholders.
- Designed longitudinal causal frameworks quantifying the financial value of CX improvements. Built quantitative analysis models in Python and R, modeling relationships between product implementation, adoption, and renewal outcomes.
- Synthesized customer feedback with operational and transactional data to identify root causes of recurring issues using SQL-based data pulls; developed action plans, produced remediation reports, and measured effectiveness against KPI targets.
- Conducted A/B testing and multivariate analyses, quantifying causal impact on retention with structured hypothesis validation. Utilized AI tools to accelerate analysis and communicated findings through data visualization.
Technologies: Tableau, Python, R, SQL
Senior Business Analyst, Workload Analytics
2017 - 2018
Teradata
- Partnered with data science teams to develop and validate an automated reasoning system that used internal telemetry to recommend database performance and capacity improvements.
- Used SQL to analyze database workload and performance data, translating complex telemetry into actionable findings for technical and business stakeholders.
- Applied Python and R for quantitative analysis and developed data visualizations and proof-of-concept prototypes to demonstrate proposed solutions to key stakeholders.
- Gathered customer feedback and translated business requirements into technical specifications, aligning enterprise needs with product and data science teams.
Technologies: SQL, Python, R
Experience
Stylin'
https://github.com/IsabelEscobarRivas/stylin-I designed and implemented a multi-agent AI platform that transforms fashion inspiration into personalized shopping recommendations. Users provide an image or text prompt, and a Vision Scout agent extracts style attributes while a Style Curator agent assembles coordinated looks across budget, mid-range, and premium price tiers.
The system creates a persistent StyleProfile that captures user preferences and supports increasingly personalized recommendations. I contributed to the product concept, agent workflow, structured data model, technical architecture, API integration, and prototype development. The project was recognized as a 3rd-place finalist in the Complete AI Hackathon hosted by lablab.ai and Complete.dev.
The system creates a persistent StyleProfile that captures user preferences and supports increasingly personalized recommendations. I contributed to the product concept, agent workflow, structured data model, technical architecture, API integration, and prototype development. The project was recognized as a 3rd-place finalist in the Complete AI Hackathon hosted by lablab.ai and Complete.dev.
Proto Circlem, an Attribution and USDC Micropayments Engine
https://github.com/IsabelEscobarRivas/proto-circleI developed a hackathon prototype that connects transparent creator attribution with instant USDC micropayments on Arc Testnet. The application registers influencers, generates unique campaign links, records click and conversion events, resolves multi-touch attribution, and initiates blockchain payouts through Circle developer-controlled wallets.
I implemented a recency-weighted attribution model that allocates conversion value according to the timing and influence of eligible interactions, while preserving a human-readable rationale for each decision. The application includes an evidence timeline, a payout-status dashboard, REST API endpoints, transaction tracking, and Arcscan links for independent settlement verification.
I implemented a recency-weighted attribution model that allocates conversion value according to the timing and influence of eligible interactions, while preserving a human-readable rationale for each decision. The application includes an evidence timeline, a payout-status dashboard, REST API endpoints, transaction tracking, and Arcscan links for independent settlement verification.
Education
2010 - 2013
PhD in Public Policy and Administration
City University of Hong Kong - Hong Kong
2008 - 2010
Master's Degree in Public Policy
University of Erfurt - Germany
2004 - 2008
Bachelor's Degree in German
Baylor University - Waco, Texas, USA
Certifications
DECEMBER 2024 - PRESENT
Applying LLMs in Practice
Harvard SEAS Professional Education
Skills
Libraries/APIs
NumPy, Pandas, Scikit-learn, Python API
Tools
Tableau, Looker, BigQuery, Docker Compose, SPSS Modeler, IBM SPSS Statistics
Languages
SQL, R, Python
Frameworks
.NET
Platforms
Amazon EC2
Storage
SAS SQL
Other
Natural Language Processing (NLP), Large Language Models (LLMs), Retrieval-augmented Generation (RAG), GitHub Actions, Artificial Intelligence (AI), FastAPI, Analytics, SAS Stats, AI Agents, LLM Agents
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring