Page * of *

BRUNGESH B E

970-***-**** adjl7h@r.postjobfree.com www.linkedin.com/in/brungesh-be

EDUCATION

Colorado State University, Fort Collins, CO

Master of Science, Computer Science, GPA - 3.75, Graduation – May 2021 Selected Coursework: Introduction to AI (Cs440, Fall-19), Machine Learning (Cs545, Fall-19), Artificial Intelligence

(Cs540, Spring-20), Big Data (Cs535, Spring-20), Design and Data Analysis for Research (STAT511, Spring-20), Introduction to ML (Cs445, Fall-20), Software Process and Product Evaluation (Cs514, Fall-20) JSS Academy of Technical Education, Bangalore, India Bachelor of Engineering (Hons.), ECE, July 2017, GPA-3.3 SKILLS

Languages: Python, Java, C++, C, R, HTML, CSS, Bootstrap, Javascript, Machine Learning, NLP Data Science libraries: Pandas, Numpy, Scipy, Matplotlib, Tensorflow, Keras, Pytorch, Spacy, NLTK, REST API Python Frameworks: Django and Flask for web application development IDE’s: Jupyter notebook, Spyder, Eclipse, IntelliJ, Rstudio, Pycharm, Matlab Tools: Robomongo, Docker, Jenkins continuous integration, AWS S3 bucket, Github, Bitbucket Big Data tools: Apache Spark, Apache Storm, Apache Hadoop, Apache ZooKeeper, HDFS, Map-Reduce Database Systems: MySQL, MongoDB

Operating Systems & software: Linux, Windows, Microsoft Office - Word, Excel, Outlook, PowerPoint, Access EXPERIENCE

Graduate Research Assistant, Jan ‘20 - May ‘20

Colorado State university, Fort Collins

• In collaboration with the Dept of Biology under Dr.Montgomery Tai, I assisted in the development of a data processing pipeline (in Python) for small RNA sequencing.

• The pipeline known as AQuATx (Automated QUantitative Analysis of Transcript eXpression) is a set of tools to simplify the analysis of next-generation sequencing data. The goal of this specific repository is to provide an entire workflow for processing small RNA sequencing data. Software Developer, Oct ’17 – Jul ‘19

Accenture Solutions Pvt Ltd, Bangalore, India

• Developed modules to convert PDF files into JSON readable format. Developed various features for the PV application according to client requirements. Worked with Senior Developers in AI team to create architectural framework and to train machine learning models.

• Fix production Bugs within a stipulated timeframe. Work closely with business analyst, quality assurance, and project management resources throughout delivery of solutions. Also have experience of facing customers while requirement gathering, discussing process flow and User Acceptance Tests and bug fixes.

• Successfully designed Machine Learning models as part of the AI team. Encapsulated the models in docker containers and deployed it development and QA servers via Jenkins. Worked extensively on natural language processing libraries like nltk, spacy etc.

• Extensive work experience in executing all phases of software life cycle starting with stake holder requirement gathering, technical design documentation, analysis, development, implementation, unit testing, maintenance, Hosting and Release management and Production Support. Experienced in defect management and Application Life Cycle Management as a developer.

Summer Intern, Jan ’16

Experts Hub, Industry Skill Development Centre, Bangalore, India

• Built a mobile app as well as a Web app for Automation of Street lights Control and Light Intensity Monitoring using IOT Technology. The user is provided with manual as well as automatic control via of lights via web & mobile app. The aim is to reduce the usage of non-renewable energy resources, thereby attempting to make optimum consumption of said resources.

Page 2 of 2

PROJECTS

Pharma co-vigilance

Accenture Solutions Pvt Ltd, Mar ‘18

• Developed drug and entities module as part of the AI team in the PV First application using Python and Machine learning algorithms. This in-house application helps global pharma companies to source, process, report and predict adverse event cases to the safety databases on an AI platform. Airline Twitter Sentiment Analysis and Topic Segregation using Machine Learning Algorithms Colorado State University, Fall ‘19

• In this project, we used Kaggle dataset of Twitter US Airline consisting tweets of 6 major US airlines. We processed the data and visualised it using word cloud distribution. The classification algorithms used were Multinomial Naïve bayes, SVM, Random forest, Logistic Regression and VADER algorithms. Text Classification and Prediction using word N-gram models Colorado State University, Fall ‘19

• Classified text readings based on various authors and did sentence prediction matching the author’s writing style. Object Detection and Image Segmentation with Mask R-CNN Colorado State University, Spring ‘20

• In this project, we have trained a mask R-CNN to recognize a raccoon, through transfer learning by using the pre- trained weights of the mask R-CNN trained on the COCO dataset. Additionally, we have simulated the bokeh effect on the detected objects using their masks.

Implementing Lung Cancer Detection using Convolutional Neural Networks on Distributed systems Colorado State University, Spring ‘20

• In this project, we trained high resolution 3D chest CT scans to our convolutional neural network model to detect whether the tumour present in a patient’s lung is malignant or benign i.e, to predict the likelihood of a patient having lung cancer. One of the main objectives of this project was to implement tensorflow in distributed systems.

Hyperlink-Induced Topic Search (HITS) over Wikipedia Articles using Apache Spark Colorado State University, Spring ‘20

• In this project, we designed and implemented a system that generates a subset of graphs using Hyperlink-Induced Topic Search (HITS) over currently available Wikipedia articles.

• The goal of this was to install and use Analytics tools like HDFS and Apache Spark. We generated the root set and base set based on the available link information and implemented iterative algorithms to estimate Hub and Authority scores of Wikipedia articles using Wikipedia dump data. Detecting the Most Popular Topics from Live Twitter Message Streams using the Lossy Counting Algorithm with Apache Storm

Colorado State University, Spring ‘20

• In this project, we designed and implemented a real-time streaming data analytics system using Apache Storm. The goal of this project was to detect the most frequently occurring hash tags from the live Twitter data stream in real- time. And also, to understand and implement parallelism over a real-time streaming data processing framework.

Contact this candidate