Toxicokinetics studies.. (toxicokinetics evaluation in preclinical studies)
Resume
1. PARMANAND SAHU
Dallas,TX | parmanand.sahu@utdallas.edu | 972-730-3967 | linkedin.com/in/parmanandsahu/ | github.com/analystanand
EDUCATION
THE UNIVERSITY OF TEXAS AT DALLAS, Richardson, TX Aug 2019 - May 2021
Master of Science in Computer Science 3.61/4
Related Coursework: Machine Learning, Database Design, Algorithms and Data Structure, CNN
NATIONAL INSTITUTE OF TECHNOLOGY, Raipur, IN Jul 2009 - Jul 2013
Bachelor of Technology (Hons.) in Metallurgical Engineering 8.35/10
TECHNICAL SKILLS
Languages Python, C, MATLAB, Node.js
Databases MongoDB, MySQL, DynamoDB, Neptune, ElasticSearch, Neo4j
Libraries Numpy, Pandas, Matplotlib, NLTK, Gensim, Sklearn, Spacy, Scipy, Tensorflow, PyTorch
Algorithms Random Forest Logistic Regression,SVM, K-means,Decision Tree, RNN, Attention Mechanism, Anomaly Detection
Technologies Linux, Git,Jupyter Lab, RASA, Docker, MS-Excel, ML-flow, ELK, Django, Rest, Spark, Flask
WORK EXPERIENCE
Capital One Jun 2020 - Aug 2020
Data Science Intern McLean,VA
Mortgage Based Security Prepayment Model (Pandas | DNN | AWS S3 | Tensorflow | Matplotlib)
– Analyze and preprocesses specific category of Mortgage Based Securities(MBS) with 150+ features
– Train and evaluate Neural Network model on preprocessed MBS data
– Automate report generation for evaluation of models for comparison
VHSS Lab at Center for Modeling and Simulation, UTD Sep 2019 - May 2020
Machine Learning Specialist | Student Assistant Richardson,Tx
Conversational Emotive Virtual Reality patient (NSF funded)(Transformer | Virtual Assistant)
– Research and Train transformer-based model for virtual patients interacting with medical students using Pytorch.
– Supervise a project for assessing medical students based on their responses to virtual patients.
Huddl Enterprise Communication Pvt. Ltd Apr 2018 - Jun 2019
Artificial Intelligence Engineer Hyderabad, India
Named Entity Recognition for Voice Assistant(Python | Node.js | Regex | DynamoDB | Virtual Assistant)
– Supervised data preparation team and retrained custom spacy model for Named-Entity-Recognition.
– Built module using Levenshtein Distance and Phonetic similarity to fix incorrect transcription for recognized entities.
– Developed micro-service using Node.js and DynamoDB to use as gazetteer in NER.
– Designed module using regex for extracting entities like Time and Date from voice commands.
Reverse image search for information retrieval(Elastic Search | K-means | Neptune | OCR | Sci-kit )
– Developed parser for OCR response and utilized K-means to classify content to reduce false positive.
– Built keyword extraction using RAKE and graph-based algorithm for ranking meetings on search results.
Action Item Detection in Meeting Transcript(Python | LSTM | RNN | Mlflow)
– Trained LSTM-RNN based model to classify the action items in the meeting transcript 95%.
– Deployed ML-flow for internal use and track experiments with multiple hyper-parameters.
CoArtha Technosolution Pvt. Ltd. Sep 2017 - Apr 2018
Associate Data Science Engineer Hyderabad, India
Semantic Understanding of Job Description for ranking resumes (Python | Naive Bayes | Beautiful Soup)
– Built pipeline to scrape 10+ job boards and pre-processed data using Selenium and Beautiful Soup.
– Trained model using Naive Bayes to classify sentences in job desc. & polarity with 90%+ acc.
– Assisted in developing scoring logic to match job descriptions with resumes.
Candidate screening from audio interviews (Python | Random Forest | Librosa)
– Employed Random Forest for classifying candidates using interview response audio with 90+% acc.
2. CoArtha Technosolution Pvt. Ltd. Sep 2016 - Aug 2017
Associate Software Engineer Hyderabad, India
Knowledge Graph from job descriptions for ranking resumes (Python | Neo4j | ElasticSearch| MongoDB)
– Built Knowledge graph using Neo4j with skills, job titles & education entities from 100k+ job descriptions.
– Designed pipeline to semi automatically update knowledge graph for resume ranking.
Semantic parsing of resumes(Python | Regex | Logistic Regression | TF-IDF)
– Trained ensemble model to identify sections(contact, education, experience and skill)
– Implemented solution using regex for extracting entities and parsed table to correlate extracted entities.
DigiFledged Jul 2015 - Aug 2016
Founder Bhilai, India
– Managed daily operation and acquired technical & functional requirements of projects from new clients.
– Led a team to deliver 5+ web development, 17+ freelancing projects and establish a blog with 60K+ page-views.
JSW Steel Ltd. Feb 2014 - Apr 2015
Junior Manager Bellary, India
– Analyzed production reports discovering insights through exploratory data analysis using MS Excel and R.
– Assisted in evaluating Implementation of Level 2 automation in Secondary Steel Making.
PROJECTS
Question Answering on SQUAD 1.0 (LSTM | RNN | Self Attention | Pytorch)
– Preprocessed and extracted custom features along with pre-trained word embedding(Glove). embedding(Glove).
– Trained QA model(simplified Stanford Attentive Reader) with 70% F1 Score.
Credit Card Transaction Fraud Detection(Random Forest | Logistic Regression | Feature Engineering | Sci-kit)
– Imputed missing data,created custom features,normalize and encode features
– Performed exploratory data analysis of features
– Handled imbalanced data using SMOTE and custom loss function.
– Train and evaluate linear/tree based classifier methods
– Analyzed feature importance w.r.t to dependent variable
Named Entity Recognition on CONLL 2003 (RNN | GRU | Pytorch)
– Preprocess and prepare vocabulary for embedding layer
– Trained and compared Vanilla RNN(83%) and GRU RNN(86%)
Image Identification on CIFAR-10 dataset (Pytorch | Convolutions Neural Network )
– Augmented image data using transformation technique(random crop,vertical flip)
– Implemented and trained RESNET family of architecture for image detection with 86% accuracy
Ensemble Method and Decision Tree from scratch (Decision Tree | Bagging | Adaboost | Sci-Kit)
– Implemented fixed depth decision(ID3) tree from scratch for monk’s classification dataset
– Implemented Bagging and AdaBoost and compared with Sci-kit implementation for Mushroom bruises
Web Development and Deployment
– Developed MVC based web application for managing contacts using Django
– Deployed Serverless Web Application using AWS Lambda, Amazon API Gateway, Amazon Dynamo-DB, Amazon
Cognito, and AWS Amplify Console.
CERTIFICATIONS AND ACTIVITIES
– Data Scientist with python track by DataCamp
– Architecting in AWS by The University of Texas at Dallas
– PyTorch, SQL, Django offered through Linkedin Learning
– Volunteered for Lone Star Parity Project for technical assistance.
– Linked Data Engineering by Hasso-Plattner Institute: Building Knowledge Graph,2016.
– M101: MongoDB for Developers by MongoDB University
– Neural Network and Deep Learning and Machine Learning offered through Coursera
– Volunteered as Member of AnalyticsVidhya.com (Data Science Community, Hyderabad Chapter.)
– Digital Marketing Certification from Delhi School of Digital Marketing, Delhi, INDIA.