Lucas Pavanelli

Data Scientist/Software Engineer Intern

Jobzi•  May 2017 - April 2019

• Jobzi (http://jobzi.com) is a tech startup based in Rio de Janeiro that aims to provide smarter ways of matching jobs and candidates using Machine Learning techniques. • Implemented search algorithm using Solr. Improved search time in 50% and results quality in 30%. (Java and Python) • Used NLP techniques to recommend skills for resumes. (Python) • Improved company’s infrastructure using microservices and applications such as ELK, Sleuth and Zipkin. Decreased build time in 100% and debug time in 50%. (Java) • Worked on job’s salary identification using gradient boosting and metrics such as precision and recall to evaluate proposed method. Improved recognition from 70% to 90%. (Java and Python)

Undergraduate Research

Pontifical Catholic University of Rio de Janeiro•  July 2015 - July 2017

• Developed a stochastic simulation system for Petrobras, under the orientation of Eduardo Laber and Hélio Lopes. Allowed them to save hundreds of thousands of dollars in the investigation of wells to be drilled. (C/C++) • Participated in a machine learning project aimed at improving the selection of attributes to split data in decision tree. (Python) • On Compression Techniques for Computing Convolution - DOI: 10.1109/DCC.2016.82 – Co-authored a paper pub- lished and presented at Data Compression Conference (DCC) 2016. Provided an investigation of the potential of Run Length Encoding and Lempel-Ziv based methods for efficiently computing convolutions between a sequence of patterns and a given image. • LSHSIM: A New Method for Multiple-Point Geostatistics - DOI: 10.1016/j.cageo.2017.06.013 – Co-authored a paper published in Computers and Geosciences journal done as a result of Petrobras project. It is about using Locality Sensitive Hashing for Multiple-Point Geostatistics.

Pontifícia Universidade Católica do Rio de Janeiro, Rio de Janeiro

Computer Science & Engineering, BE•  March 2015 - December 2019

• B.S.E. in Computer Engineering with Minor in Mathematics, GPA 8.2/10.0. • Final Project: Segmentation of unstructured textual data using HMM. Developed an algorithm inspired in the Viterbi algorithm to segment a resume in sections like Personal Data, Work Experiences, Education.