Tiago Kuniyoshi

Data engineer

Florianópolis, Brazil

Summary

I've always been studying the impact of technology in our society. So one year and a half ago, I decided to work directly with machine learning and started my tech startup during university graduation. On June 2018, I worked in a project in the university that aimed to help technology startups innovate with machine learning. Over there I built a recommendation system that integrates with their platform. In December 2018 I got hired by Keyrus, one of the largest big data consulting companies in the world, and worked with machine learning proof of concepts for customers that were starting with the technology. Today, I'm still working on my startup and I'm looking for a job in the data field.

Languages:

English, Portuguese, Spanish

Experience

Employment

Entrepreneur Bankai (startup) Mar/18-current

• Building a Minimum Viable Product for market validation.
• Act as Scrum Master and developer working on backend, data science, database, frontend and infrastructure.

Autonomous, machine learning Keyrus Dec/18-Apr/19

• Built a pioneer proof of concept for the customer implementing a machine learning script with data collected from the web.
• Trained team with basic knowledge of Machine learning.

Intern Project “Data Mining for technology startup Jun/18-Nov/18

• Designed and implemented a recommender system for the customer Linx Impulse.

Projects

App for user match

• Created a RESTful API with register, login, authentication, automatic email sending, forms, image uploading and recommender system.
• Built scalable infrastructure supporting backend, frontend and load balancer.
• Integrated frontend requests with the API and built features.
• Utilized: Git, Unix, Python, Flask, PostgreSQL, Javascript (React), Kubernetes, Docker, Jenkins, Nginx

Bus arrival prediction (github.com/tiagoshin/Bus-arrival-prediction)

• Designed and built a predictor for bus arrival time using gathered data from Rio Data API collected in 5 to 5 minutes.
• Utilized: Spark, regression, MongoDB

Audience expansion recommender system

• Designed a proof of concept for the implementation of a new recommender system that aims to provide the top-k consumers in the general public for a given segment.
• Utilized: Python, classification, recommender systems

See github.com/tiagoshin for more

Education

UFSC Jan/14-Dec/18

• Major: Industrial engineering, incomplete
• Coursework: Statistics, probability, calculus, algebra, operational research.

Skills

• Data Science (proeficient): Python (pandas, numpy, scikit-learn), Pyspark, Classification, Regression, Clustering, Recommender systems (familiar): SQL, SparkR, MongoDB, PostgreSQL
• Software (proeficient): Git, Unix, Flask (familiar): Javascript (React), Nginx
• Infrastructure (proeficient): Kubernetes, Docker, Jenkins, AWS EC2, Google Cloud
• Language: Portuguese, English, Spanish

Skills

Amazon Web Services (AWS), Artificial Intelligence, Backend Development, Big Data, Data Science, DevOps, Docker, Flask, Git, Google Cloud Platform (GCP), Jenkins, Kubernetes, Linux, Machine Learning, Nginx, NumPy, Pandas, PostgreSQL, ReactJS, SQL, SQLAlchemy, Spark, Visualization, uWSGI