Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I'm Andrew Santoli. I'm a Senior Data Engineer & Scientist with 10+ years of experience turning complex data into actionable insights across healthcare, marketing, AI, and blockchain. I specialize in real-time pipelines, ML-powered feature stores, and predictive analytics that drive measurable business outcomes. I'm passionate about mentorship, product innovation, and enabling data-driven decisions that accelerate growth, optimize operations, and boost revenue.…Hi, I'm Andrew Santoli. I'm a Senior Data Engineer & Scientist with 10+ years of experience turning complex data into actionable insights across healthcare, marketing, AI, and blockchain. I specialize in real-time pipelines, ML-powered feature stores, and predictive analytics that drive measurable business outcomes. I'm passionate about mentorship, product innovation, and enabling data-driven decisions that accelerate growth, optimize operations, and boost revenue.

Andrew Santoli

Full Stack Developer, Data Scientist, Blockchain Developer, +3





Hi, I'm Andrew Santoli. I'm a Senior Data Engineer & Scientist with 10+ years of experience turning complex data into actionable insights across healthcare, marketing, AI, and blockchain. I specialize in real-time pipelines, ML-powered feature stores, and predictive analytics that drive measurable business outcomes. I'm passionate about mentorship, product innovation, and enabling data-driven decisions that accelerate growth, optimize operations, and boost revenue.…Hi, I'm Andrew Santoli. I'm a Senior Data Engineer & Scientist with 10+ years of experience turning complex data into actionable insights across healthcare, marketing, AI, and blockchain. I specialize in real-time pipelines, ML-powered feature stores, and predictive analytics that drive measurable business outcomes. I'm passionate about mentorship, product innovation, and enabling data-driven decisions that accelerate growth, optimize operations, and boost revenue.

Available to hire

Hi, I’m Andrew Santoli. I’m a Senior Data Engineer & Scientist with 10+ years of experience turning complex data into actionable insights across healthcare, marketing, AI, and blockchain. I specialize in real-time pipelines, ML-powered feature stores, and predictive analytics that drive measurable business outcomes.

I’m passionate about mentorship, product innovation, and enabling data-driven decisions that accelerate growth, optimize operations, and boost revenue.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Work Experience

Data Scientist at Santoli Connected Network

June 1, 2024 - Present

Led a unified ML feature store consolidating 12 fragmented behavioral datasets in AWS/Snowflake, reducing model prep time from 4 hours to 12 minutes and improving personalization accuracy. Built multimodal transformer models (text, image, audio) using PyTorch/HuggingFace, boosting ranking quality by 18% and delivering actionable marketing insights. Deployed real-time inference endpoints on AWS Lambda/API Gateway with latency under 250ms, enabling immediate personalization for millions of daily interactions. Collaborated with product leadership to define Bayesian experiment metrics, shortening feature iteration cycles. Implemented automated model drift monitoring and data quality checks with SageMaker and Great Expectations, reducing false positives by 32%. Created interactive dashboards with Streamlit & Plotly to quantify ROI and support pricing decisions. Mentored two junior engineers on ML pipelines.

Senior Blockchain Data Engineer / Blockchain AI Analytics Engineer at Blocknative

October 1, 2021 - May 1, 2024

Designed real-time multi-chain pipelines (Kafka, Flink, Web3 APIs) processing 10M+ daily transactions, delivering DeFi and NFT insights for traders and institutions. Architected Snowflake & BigQuery warehouses with partitioning/clustering, cutting large dataset query times by 40%. Implemented hybrid storage (ClickHouse + PostgreSQL) to optimize speed and reliability for blockchain data. Built predictive ML models (TensorFlow, XGBoost) for gas fees, congestion, and delays; developed anomaly detection with PyTorch to flag suspicious contracts. Automated serverless ETL pipelines on AWS Lambda/S3, reducing operational costs while scaling indexing. Built dashboards (Power BI & Superset) visualizing NFT markets, whale activity, DeFi lending risks. Led multi-cloud deployment & CI/CD (Terraform, GitHub Actions, Kubernetes) ensuring high availability and zero downtime. Mentored 3 engineers.

Data Engineer at Athenahealth

September 1, 2018 - August 1, 2021

Designed real-time pipelines (Airflow, Kafka, Spark) processing EHR, wearable, and vitals data, improving AI analytics efficiency by 30%. Architected Snowflake data warehouse + AWS S3 data lake with Redshift Spectrum, centralizing healthcare data access and boosting query performance 5×. Built ML models (XGBoost, Random Forest, Deep Learning) predicting sepsis, readmission, and chronic disease progression; applied LSTM & Prophet time-series models to reduce ICU overflow by 12%. Deployed ML models on AWS SageMaker with real-time inference endpoints; built feature stores with Snowflake & Redis for consistent ML operations. Implemented Kafka Streams for real-time anomaly detection, enabling faster interventions and higher patient safety. Automated regulatory reporting and ML feature engineering using Python & Docker, increasing compliance efficiency and model accuracy.

Data Analyst at Click&Boat

February 1, 2016 - August 1, 2018

Built automated dashboards (Power BI, Tableau) monitoring ad spend, revenue, and profitability, increasing ROI by 16% while reducing unnecessary spend by 10%. Forecasted revenue trends with SQL/Python, improving budgeting accuracy by 15% during peak seasons. Ran A/B tests for ad strategies, boosting conversions by 20% without increasing spend. Automated ETL pipelines (Airflow, AWS Lambda) and CI/CD workflows, cutting manual processing time by 43%.

Business Intelligence Specialist at Red Carpet Corp

June 1, 2013 - December 1, 2015

Automated ETL workflows & dashboards (SSIS, Python), reducing reporting prep time by 6×. Performed cohort and funnel analysis using Looker, uncovering customer lifetime value patterns and boosting campaign profitability by 14%. Built forecasting models for seasonal campaigns, improving budget allocation accuracy. Partnered with marketing teams to define KPIs (CAC, ROAS), reducing wasted ad spend by 9%.