Pedro Toledo Email & Phone Number

State Of Minas Gerais, Brazil

Belo Horizonte, Minas Gerais, Brasil

Belo Horizonte, Minas Gerais, Brasil

• Contributed to the technical development of the data science team• Contributed to the development of new tech leads in data science within the company• Ensured the technical excellence in data science projects• Gave technical support to data science projects• Helped to establish the company as a technical reference in data science• Helped to develop the company's culture within the team

• Developed data science projects in the industrial and food retail business, which involved deep business understanding, ETL, exploratory data analysis, machine learning modeling and deployment alongside key business partners;• Developed processing pipelines for large scale datasets, using tools like Apache Spark and the resources provided by cloud computing;• Contributed to the development of colleague’s projects with technical and business insights;• Lectured on the use of PySpark for processing massive data, as well as on how to use Streamlit for deploying machine learning solutions on an interactive app;• Contributed to several of the company's open source Python libraries (Hermione, Rony), including a full module that wraps pyspark.ml helpers and functionalities.

Taught the "Big Data Tools: Massive Data Processing" class in two periodic bootcamps, in which lectured on how to use Apache Spark for the development of large and scalable data pipelines for both on-premises and on-cloud environments. Produced 14 hours worth of recorded classes and a 176 page long original manual for the course, and its contents included:• Distributed computing, basic concepts; • Introduction to Apache Hadoop Ecosystem, Architecture and main components; • Apache Spark, concepts, installation and configuration; • Apache Spark uses: PySpark, Spark SQL, Scala; • Reading and writing files of different formats (CSV, json, parquet, ORC); • Data partitioning strategies; • Spark optimization techniques; • Scalable architectures; • Concept and types of scalability.

Belo Horizonte E Região, Brasil

Participated in several data science projects, actively working in data analysis, visualization and modeling. Activities: • Manipulation of large amounts of data;• Development of Machine Learning models (regression, segmentation/clustering, classification, dimensionality reduction, optmization);• Data analysis;• Development of ETL processes;• Creation of metrics;• Results presentation;• Development of an internal Python library for the company.

Participated in the analysis of survey results and the development of predictive models.Activities:• Development of predictive models, using statistical and machine learning methods;• Manipulation of large amounts of data;• Extraction and structuring of large amounts of data using software such as Microsoft SSIS and IBM Modeler;• Data analysis and dashboard creation, using R and Power BI.

Bachelor'S Degree, Statistics

Master Of Business Administration - Mba, Digital Business, 10