Data Science, ML, and engineering applied to Health and Biological data sources.
Analytics and Machine Learning applied to:
CERTIFICATIONS
2021-06
Databricks Data Engineer + Data Analyst Certifications
2021-06
Databricks Developer for Apache Spark 3.0 Certification
2021-01
Google Analytics for Power Users Certification
2020-10
Google Machine Learning Engineer Professional Certification (102nd Worldwide)
2017-12
Agile ScrumMaster Certification
Scrum Alliance
2017-11
Google Data Engineer Professional Certification (502nd Worldwide)
Data Professional Experience
Technical Capabilities
Business Capabilities
SKILLS
Data Methods
Related to AI Projects
Conversational Analytics: At Info2data com, I am working on an AI Agent solution for Data Analytics discovery in environments with a high diversity of data sources scalable to more than 400 hundred analysts. This requires connecting to and orchestrating multiple systems like Bigquery, Vertex Search (RAG), Relational Databases (PostgreSQL), and Files (Storage, Drive), using Cloud Workflow to feed Chat Assistants built with ADK (Agent Development Kit) framework, mirroring the goal of having agents retrieve, combine, analyze, and generate insights across various applications. This work included developing a Model Context Protocol (MCP) backend using FastAPI to connect with Relational Databases. Bioinformatics Master?s Degree Capstone Project: AI Conversational Analytics Agent to interact with Clinical/Hospital databases based on the OMOP CMD Standard Knowledge Base & Search Retrieval (Vector Databases): At Randstad Global, I led initiatives for RAG (Retrieval Augmented Generation) for Search Business KPIs and applied Generative AI to data governance and data discoverability, utilizing tools like Google Search AI. This involved building and orchestrating structured/unstructured datasets/documents ready for RAG and Search consumption, ensuring content is searchable and retrievable from curated sources. Because a huge part of the data came from Human Resources (curriculum vitae, etc) the area of data protection, anonymization was a key factor in the final solution. Data Pipelines design for Chat/Agent assistants: The last two projects required to build the data pipelines specifically toprovide context/metadata information to the assistants for them to use the proper tool/function that brings the numeric data in the way that the agent/chat requires (inside the main prompts, added prompts, etc). The technology used to create the pipelines is the usual: Dataflow, PubSub, Airflow, Cloud Workflow, Bigquery Dataform/DBT, plus the Vector Databases (Vertex AI Vector Search or the function included in bigquery, postgress, etc). In some of the cases, the pipelines are also required to change some API specifications to adapt the current definition to the capabilities of the chat.
SUMMARY
Data Governance and Evaluation of AI Systems:
Team and Business Oriented
Tools and Coding Skills:
Data Science, ML, and engineering applied to Health and Biological data sources.
Analytics and Machine Learning applied to:
CERTIFICATIONS
2021-06
Databricks Data Engineer + Data Analyst Certifications
2021-06
Databricks Developer for Apache Spark 3.0 Certification
2021-01
Google Analytics for Power Users Certification
2020-10
Google Machine Learning Engineer Professional Certification (102nd Worldwide)
2017-12
Agile ScrumMaster Certification
Scrum Alliance
2017-11
Google Data Engineer Professional Certification (502nd Worldwide)
Data Professional Experience
Technical Capabilities
Business Capabilities
SKILLS
Data Methods
Related to AI Projects
Conversational Analytics: At Info2data com, I am working on an AI Agent solution for Data Analytics discovery in environments with a high diversity of data sources scalable to more than 400 hundred analysts. This requires connecting to and orchestrating multiple systems like Bigquery, Vertex Search (RAG), Relational Databases (PostgreSQL), and Files (Storage, Drive), using Cloud Workflow to feed Chat Assistants built with ADK (Agent Development Kit) framework, mirroring the goal of having agents retrieve, combine, analyze, and generate insights across various applications. This work included developing a Model Context Protocol (MCP) backend using FastAPI to connect with Relational Databases. Bioinformatics Master?s Degree Capstone Project: AI Conversational Analytics Agent to interact with Clinical/Hospital databases based on the OMOP CMD Standard Knowledge Base & Search Retrieval (Vector Databases): At Randstad Global, I led initiatives for RAG (Retrieval Augmented Generation) for Search Business KPIs and applied Generative AI to data governance and data discoverability, utilizing tools like Google Search AI. This involved building and orchestrating structured/unstructured datasets/documents ready for RAG and Search consumption, ensuring content is searchable and retrievable from curated sources. Because a huge part of the data came from Human Resources (curriculum vitae, etc) the area of data protection, anonymization was a key factor in the final solution. Data Pipelines design for Chat/Agent assistants: The last two projects required to build the data pipelines specifically toprovide context/metadata information to the assistants for them to use the proper tool/function that brings the numeric data in the way that the agent/chat requires (inside the main prompts, added prompts, etc). The technology used to create the pipelines is the usual: Dataflow, PubSub, Airflow, Cloud Workflow, Bigquery Dataform/DBT, plus the Vector Databases (Vertex AI Vector Search or the function included in bigquery, postgress, etc). In some of the cases, the pipelines are also required to change some API specifications to adapt the current definition to the capabilities of the chat.
SUMMARY
Data Governance and Evaluation of AI Systems:
Team and Business Oriented
Tools and Coding Skills: