Jose Andrade

Sr. Data Engineer

San Jose, CA 95148 | [email protected] | (408) 641 - 6660

PROFILE SUMMARY
I started my professional journey as a Software Engineer who built back-end systems and APIs, but discovered that
my true passion was working with data to influence decision making. This discovery ultimately brought me to Data
Engineering, where I was able to use my technical skills to develop exciting data outcomes. As a Senior Data Engineer,
I am responsible for developing scalable data pipelines, building AI systems, and automating workflows that detect
operational efficiencies. I have hands-on experience with tools like Python, TensorFlow, and Databricks, I've used
Machine Learning and Natural Language Processing (NLP) to solve intricate problems in various industries like
healthcare and gaming. I go from developing real-time event-streaming systems to using AI to augment data insights.
Ultimately, I am working to make data and AI more broadly available so organizations make that much smarter, and
faster, decisions.
TECHNICAL SKILLS
Programming Languages & Frameworks
• Python, Scala, Java, R, SQL, Spring Boot, Node.js, JavaScript
Cloud Platforms & DevOps
• Google Cloud Platform (GCP): Google Cloud AI, AI Platform, BigQuery, Google Cloud Storage
• Microsoft Azure: Azure Machine Learning, Azure Databricks, Azure Blob Storage
• Amazon Web Services (AWS): SageMaker, Lambda, EC2, S3, Redshift, Glue, CloudWatch, AWS Kinesis
• CI/CD Tools: Jenkins, GitLab CI, Docker, Kubeflow, Kubernetes
• Cloud Infrastructure: AWS S3, AWS Redshift, AWS Lambda, Azure Blob Storage
Data Engineering & Data Science
• Data Pipelines: Apache Kafka, AWS Kinesis, Google Cloud Dataflow, Apache Airflow, AWS Glue
• Data Warehousing & Databases: Snowflake, PostgreSQL, BigQuery, MySQL, AWS Redshift
• Data Cleaning & Preprocessing: Pandas, NumPy, Scikit-learn, OpenCV
Big Data & Analytics Tools
• Apache Kafka, Spark Streaming, Apache Flink
• Power BI, Tableau, AWS QuickSight, Google Data Studio
Business Intelligence & Reporting
• Data Visualization: Power BI, Tableau, AWS QuickSight, Google Data Studio
• Reporting & Analytics: Real-time Dashboards, Custom Reports, Predictive Reporting
AI & Machine Learning (ML), NLP & LLM
• Machine Learning: XGBoost, Random Forests, scikit-learn, TensorFlow, Keras, PyTorch, AWS SageMaker,
GCP AI Platform, Azure Machine Learning
• Natural Language Processing (NLP): spaCy, Hugging Face Transformers, BERT, text preprocessing, entity
recognition, document classification, sentiment analysis
• Large Language Models (LLM): GPT-3, BERT, T5, text summarization, document understanding, entity
extraction, automated response generation
Security & Compliance
• HIPAA Compliance, OAuth2, JWT (JSON Web Tokens)

PROFESSIONAL EXPERIENCE

Senior Data Engineer

Cigna, Bloomfield, CT | May 2022 – February 2025
• Engineered AI-driven healthcare data solutions using Python, Scala, TensorFlow, Google Cloud AI, and
Databricks, improving document processing efficiency by 75% and reducing processing time by 30%,
enabling clinicians to access critical data faster.
 • Streamlined real-time data pipelines with Python, Apache Kafka, Scala, Google Cloud Dataflow, and
Databricks, reducing data integration delays by 60% and providing 500+ clinicians seamless access to
real-time patient records.
• Developed a scalable data repository in Snowflake using Python and Scala, increasing patient data
retrieval speed by 80% and improving data access for business intelligence tools, enhancing overall
workflow efficiency.
• Systematized an OCR-based system using Python, OpenCV, TensorFlow, and Java, improving the
accuracy of scanned insurance card data by 40%, ensuring accurate patient information and improving
operational efficiency.
• Guided the development of an AI-powered clinical decision support chatbot with Python, Google Cloud
Dialogflow, and Java, improving clinician response time by 25-50% and enhancing patient outcomes by
25%.
• Improved PostgreSQL and BigQuery data workflows with Python and Java, boosting query performance
by 50%, enabling real-time business intelligence reporting and fast access to data insights.
• Automated model update cycles using Python, Kubeflow, Docker, Kubernetes, and Databricks, reducing
deployment times by 60% and ensuring continuous updates of AI models for clinical decision-making.
• Planned real-time analytics dashboards using Power BI, AWS Glue, Lambda, S3, and Python, providing
immediate insights on patient data, enhancing decision-making for healthcare teams.
• Enforced HIPAA compliance for all AI solutions with Python and Java, maintaining secure handling of
sensitive data and improving operational efficiency by 35%.
• Directed Apache Kafka integration for real-time event streaming using Scala and Python, improving
system uptime by 20% and ensuring smooth data flow even during high-demand periods.
• Guided cross-functional collaboration to automate healthcare data processing tasks using Python, Scala,
and Databricks, reducing operational costs by 40% and enhancing system resilience using CI/CD tools
like Jenkins and GitLab CI.
• Initiated LLM-based document summarization systems using GPT-3 and BERT, fine-tuning these
models on domain-specific medical data to extract critical information from unstructured healthcare
documents, improving summarization accuracy by 30% and reducing clinician workload.
• Spread NLP pipelines using spaCy and Hugging Face Transformers, applying BERT for entity extraction
and GPT-3 for automated patient record summarization, resulting in a 25% improvement in processing
time for unstructured medical data.
• Generated real-time NLP models using BERT and Transformers to classify clinical texts and patient
records into predefined categories, reducing data processing time by 25% and enhancing workflow
efficiency.

Senior Data Scientist

Niantic Inc., San Francisco, CA | June 2018 – April 2022
• Evolved predictive models using XGBoost, Random Forests, and scikit-learn, improving player
retention by 25% by predicting player behavior and providing personalized in-game recommendations.
• Designed and enforced real-time analytics pipelines with Python, Apache Kafka, Spark Streaming, and
AWS Kinesis, processing over 100 million player events daily, reducing data latency by 35% and
providing real-time insights into player behavior.
• Constructed a real-time anomaly detection system using the ELK Stack (Elasticsearch, Logstash,
Kibana) and Python, improving server uptime by 20% and minimizing disruptions during high-traffic
events for millions of players.
• Created an AI-powered recommendation system using collaborative filtering and content-based models,
increasing player engagement by 10% by suggesting customized in-game content based on player history.
 • Led the development of real-time dashboards with Tableau and Power BI, providing actionable insights
for game developers and business stakeholders, resulting in a 15% improvement in player retention.
• Cooperated Snowflake to optimize the data warehousing architecture for gaming analytics, improving
query throughput by 70%, enabling faster data retrieval for business intelligence and real-time analytics.
• Architected a Snowflake-based solution to centralize player data, integrating event data, player actions, and
gameplay metrics from multiple sources, providing a single source of truth for real-time analysis and
reducing data processing times by 40%.
• Generated and maintained automated ETL pipelines with AWS Glue, Python, and Apache Airflow,
processing millions of events per day and ensuring high data integrity for downstream analytics and machine
learning models.
• Optimized Snowflake queries for complex multi-table joins and aggregations, leveraging AWS Redshift to
significantly improve performance and reduce compute costs by 30% while handling large-scale gaming
event data.
• Collaborated with cross-functional teams to create a scalable data lake architecture using AWS S3 and
Snowflake, allowing efficient storage and access to petabytes of player event data for advanced analytics.
• Streamlined in-game features using machine learning models built in Python and deployed via AWS
SageMaker, improving gameplay satisfaction by 12% by offering players personalized experiences and
recommendations.
• Integrated NLP techniques (using spaCy and BERT) to analyze player feedback, identifying key pain
points and driving strategic product improvements, resulting in a 15% increase in overall player satisfaction.
• Applied time-series forecasting techniques using AWS Forecast to predict player churn and optimize
engagement strategies, contributing to 18% reduction in churn and enhancing targeted retention efforts.
• Guided A/B testing initiatives with AWS CloudWatch to assess the effectiveness of in-game features and
marketing campaigns, resulting in a 12% increase in in-game purchases and optimizing monetization
strategies for the gaming platform.
• Mentored junior data scientists, providing guidance on model development, experimentation, and data-driven
decision-making, fostering a culture of continuous learning and improvement within the gaming industry.

Data Scientist
Adecco Group, Jacksonville, FL | April 2014 – May 2018
• Built business intelligence applications with Python, SQL, Azure, and Tableau, supporting clients in
improving access to data and reporting processes to speed up their decision-making processes.
• Established interactive dashboards with Power BI and Tableau, which enabled clients to track relevant
metrics and also increased teamwork productivity by 15%.
• Participated in integrating and connecting client databases with BI tools, increasing the accuracy of data and
decreasing time spent on reporting.
• Designed data models in SQL Server, AWS Redshift, and Azure SQL Database that minimized retrieval
time for data and simplified reporting.
• Helped automation for the process of getting data from multiple sources to a usable format using tools such
as Python and SQL, to prepare the data for analysis.
• Contributed with machine learning techniques, such as XGBoost and Random Forests, to generate
predictive models that provided customer behavior insights and helped decrease churn.
• Collaborated with business units to generate Actionable Insights from data that impacted decision making
and assisted in the adoption of new BI features from clients.
• Mechanized data cleaning and preparing tasks using Python and Pandas to enhance productivity and data
precision
 • Assisted set up real-time data monitoring systems using Apache Kafka and AWS Lambda, so clients
could get immediate updates on their performance.
• Ran A/B tests on marketing campaigns, offering BI-driven recommendations that helped clients improve
customer engagement and increase ROI.
• Provided hands-on training for clients on using Power BI and Tableau, enabling them to independently
generate reports and insights.
• Produced dynamic reports using Power BI, helping client teams better track project progress and enhancing
visibility across departments.
• Analyzed large datasets with R and Python to deliver insights that supported clients identify inefficiencies
and reduce operational costs.

Software Engineer
Truelogic Software, New York, NY | May 2011 – March 2014
• Planned and implemented back-end services using Java, Spring Boot, and RESTful APIs, improving
system efficiency and ensuring scalability for client-facing applications.
• Undertook front-end functionality using JavaScript and Node.js, integrating with back-end services to
ensure seamless user experience and enhancing overall system performance.
• Initiated microservices architecture for scalable applications, leveraging JavaScript for asynchronous
processing and event-driven models, leading to a 20% improvement.
• Developed and upheld databases using MySQL and PostgreSQL, ensuring data integrity and optimizing
query performance, reducing query response time by 30%.
• Enhanced existing legacy code by refactoring and improving performance, reducing load times by 25% and
enhancing maintainability.
• Executed security best practices using OAuth2, JWT for secure user authentication and authorization,
safeguarding sensitive client data and meeting compliance standards.
• Performed system integrations with third-party services, leveraging REST APIs and SOAP to ensure
smooth communication between platforms, enhancing functionality for end-users.
• Automated deployment processes using Jenkins and Docker, leading to a 40% reduction in deployment
time, ensuring faster updates to production environments.
• Thrived unit and integration tests with JUnit, Mockito, and JavaScript-based testing frameworks (Mocha,
Jest), improving code quality and ensuring 99% test coverage for critical back-end services.
• Monitored and optimized application performance using New Relic and Prometheus, ensuring system
reliability and troubleshooting performance bottlenecks.
• Participated in Agile sprints and managed code reviews, ensuring adherence to best coding practices and
contributing to a collaborative development environment.

EDUCATION
Master of Science in Data Science University of California, United States 2020 ~ 2022
Bachelor of Science in Computer Engineering University of California (United States) 2007 ~ 2011