Machine Learning Research Associate

Research Associate DIPANKAR ROY

University of Alberta +1-780-***-**** (cell)

Biological Sciences ****.*******@*****.***

Machine Learning Engineer with 11 years of experience inworkingwithapplicationofcomputational, statistical,machine learning andnaturallanguageprocessingmethodsfordrugdevelopmentandenergy research.Proficient in cloud engineering,automation,databases,scientific programming related to multiscale modeling framework, high performance computing, datacenter managements. Nationality Canadian

Skills

Data Science/Engineering & ML/MLOps Engineering

ETL, Data pipeline for structured and unstructured data, Data Visualization (Tableau), Data Migration (on premise to cloud), Cloud storage.

Python, Tensorflow, Pyspark, Version control (GitHub). Google Cloud Platform – Bigquery, GCS, Framework: TensorFlow & Pytorch, Vertex AI. Supervised, Semi- and Unsupervised ML, NNs, NLP, Regression, Tree based models. Transfer learning- Transformer models.

Linux OS - High performance Computing.

SQL, Relational and non-relational databases, Databricks, Snowflake. Google BI Professional certification (via Coursera) Database for Data Scientists certification (Colorado University, Boulder; via Coursera) Work Experience

1.Research Associate in Predictive Modelling (University of Alberta), 2023-2016

● Built a novel computational platform for applications in neurodegenerative diseases and medical imaging;statistical modeling and machine learning in drug development using k-NN,DNN,SVM, Bayesianalgorithms,SVM,andCNN;Graphneuralnetworkformolecularrepresentationinmachine learningandautomatedhitdetectionindrugdesign;predictivemodeling,NLPforchemicalsimilarity search;developedamultiscalemodelingframeworkwiththereferenceinteractionsitesolvationmodel coupled in molecular dynamics engine and quantum mechanics interface.

● Industry Collaboration:Developing predictive modelingandstatisticalinferencecodesforChemical Computing Group, Montreal and AMBER® molecular dynamics tools with Rutgers University, USA.

● MLOps:Building an end-to-end automated ML pipeline of drug discovery projects for the Alberta Alzheimer’sResearchAssociationinGCPusingAirflow,Bigquery,VertexAI,MLFlowandserving the results via API endpoints.

● Data Engineering:Collected a large amount of patient data on neurodegenerative diseases from differentsources(CSVfromNationalInstituteofHealth[NIH],ExcelSheetsfromcollaborators,other databases from web scraping),moved to Bigquery and created a feature store:data modeling,data cleaning,dataqualitytest,removingPII,andmaintainingthisdatasetforanalysisbyourinhouseteam and collaborators, ETL for drug development.

● Software Development:Product development for “Software for Multiscale Modeling INC”.The package includes tools for applications in molecular solvation calculations with vastapplicationsin drug developments and material sciences.Additional consultancy experience in handling end user requests and implementations of new modules in the package.

● Project management (proprietary software,personnel and budget)for federally and provincially funded projects; reporting to stakeholders; presenting findings to international audiences.

● PowerBI(andMicrosoft365)experienceinbuildinganinternaldatabaseforAlzheimer’sdiseaseand metabolomicsforassemblingdatafromvariouspartnersandcreatingcustomizeddashboardsfordata Dipankar Roy Page2of 2

reporting;MS-Excel pivot tables and data analyze;Database building for opioids’ target and utilization data for reporting on project progress to funding agencies. 2.Post Doctoral fellow (City Univ of NY), 2010-2015

● Predictive modeling of bioactive peptides using Bootstrap sampling, SVM and Random Forest algorithms; developing computational chemistry tools for chemical calculations;

● Creating a relational database for molecules involved in drug discovery using MySQL.

● High performance and distributed computing (MPI and openMP) code development for quantum chemistry and molecular simulations.

Education

Ph.D. (Theoretical and Computational Chemistry): Indian Institute of Technology Bombay (IITB), India Master of Science (M.Sc.; Chemistry specialization): Indian Institute of Technology Bombay (IITB), Department of Chemistry, India

Bachelor of Science (B.Sc. Chemistry): Presidency College, Kolkata, India References available upon request.

Contact this candidate