Data Analyst with 11+ Years in ML & Analytics

DIPANKAR ROY

+1-780-***-**** (cell)

*******@*****.***

Machine LearningandComputationalPredictiveModelingwith11yearsofexperienceinworkingwith application of computational,statistical,machine learning andnaturallanguageprocessingmethodsfor drugdevelopmentandcleanenergyprojects.Proficientinprojectmanagement,businesscommunication, requirement gathering, database and cloud engineering. Nationality: Canadian

Skills

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

PowerBI, SQL, Relational and non-relational databases, Databricks, Snowflake. Python, Tensorflow, Pyspark, Version control (GitHub), R, Perl. Google Cloud Platform – Bigquery, GCS, Vertex AI, Framework: TensorFlow & Pytorch. Supervised, Semi- and Unsupervised ML, NNs, NLP, Regression, Tree based models. Transfer learning- Transformer models.

Linux OS - High performance Computing.

Work Experience

1.QED Solutions Inc. 2024-

Data science consultant: Responsibilities include

● Defining project scope, gathering business requirements and mapping business process for strategic implementation.

● Responsible for writing Business Requirement Documents (BRD), Gap analysis document and Change request documents (CR).

● Participating as an Analyst in the project for the scope and technical implementation.

● Performed Stakeholder analysis as required to understand the needs and to support team members and clients.

2.Software for Multiscale Modeling (SMModeling.com)- Scientific Advisor 2021-2024 Scientific adviser and Software developer: Responsibilities include

● Development and deployment of software packages for chemical and biological simulations

● Interfacing end-user requirements with existing product features.

● Worked with various industrial vendors to implement business/functional requirements for various application projects.

● Working closely with the project managers and industrial sponsors on time delivery of software modules with acceptable/pre-approved performance matrices.

● Wrote UAT for technical deliverables and making sure all modules and units are implemented as required

● Managed post project implementation, closing activities and follow-ups with different stakeholders and project teams.

● Translated technical results into executive reports and stakeholder-facing presentations. 3.Research Associate (University of Alberta), 2016-2023 Key responsibilities include:

● Conducteddetailedprocessanalysisofclinical/institutionalworkflows;identifiedinefficienciesand recommended automation and cloud-based improvements. Dipankar Roy Page2of 3

● Collaborated with IT,Data Engineering teams and supported deployment of data pipelines using SQL and Python

● Prepared cost-benefit analyses for cloud migration of datasets and analytics tools.

● Led efforts: training sessions, documentation creation, and stakeholder communication.

● Collected a largeamountofpatientdata(morethan1millionrows)onneurodegenerativediseases from different sources (CSV from National Institute of Health [NIH],Excel Sheets from collaborators,other databases from web scraping),movedtoBigqueryandcreatedafeaturestore: data modeling,data cleaning,data quality test,removing PII,and maintaining this dataset for analysis by our in house team and collaborators, ETL for drug development.

● PET image analysis and selective marker development for Alzheimer’s disease.

● Nuclear magnetic resonance and electron/light spectroscopy image analysis to build predictive models.

● Built an end-to-endautomatedMLpipelineofdrugdiscoveryprojectsfortheAlbertaAlzheimer’s Research Association in GCP using Airflow,Bigquery,VertexAI,MLFlowandsharedtheresults via API endpoints.

● Built a novel computational platform for applications in neurodegenerative diseases and medical imaging,did statistical modeling and machine learning in drug development using k-NN,DNN, SVM, Bayesian algorithms, SVM, and CNN.

● Developed predictive models and statistical inference codes for Chemical Computing Group, Montreal and AMBER® molecular dynamics tools with Rutgers University, USA.

● Personnel management of students,visiting scholars,and international scientists;financial report sheet preparation and management.

● Preparedscientific,financialandpersonnelrequirementsdocumentsforresearchgrantproposalsto provincialandfederalagencies(successfullyobtainedfundingworth~1millionCADovera5-year span).

4.Postdoctoral Research Associate (City University of NY), 2010-2015

● Predictive modeling of bioactive peptides using Bootstrap sampling, SVM and Random Forest algorithms; developed software tools chemical calculations.

● Created 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.

● Maintenance and administration of high-performance computing laboratory (compute clusters consists of over 2000 computing cores connected via Infiniband network adaptors) Education

Ph.D. (Computational Chemistry): Indian Institute of Technology Bombay (IITB). Master of Science (Chemical Sciences): Indian Institute of Technology Bombay (IITB). Bachelor of Science: Presidency College, Kolkata, India Key Achievements & Project Highlights

Research Requirement My Experience

Elicit & document requirements Led stakeholder workshops; produced JIRA/Confluence specs and Visio process

maps

Dipankar Roy Page3of 3

Process Analysis & Gap Identification Mapped drug development workflows; identified system/process enhancements

leading to 30% efficiency gains

Assess technology landscape Evaluated cloud data solutions and AI tools, recommending scalable adoption

Support cloud, AI, automation projects Built ETL pipelines and feature-store solutions using GCP and Python

Project planning & risk mgmt.Assisted with roadmaps, schedules, budgets; monitored risk and issue logs

Business cases & cost-benefit analysis Developed ROI analysis for research database and dashboard migrations

Change mgmt. & training Facilitated training sessions; created documentation and stakeholder

communications

Reporting & dashboard creation Delivered Power BI dashboards, KPI monitoring, and leadership reports

Certifications

Google Business Intelligence Professional

Google IT Support Professional

IBM Generative AI Professional

Database for Data Analysts,

Google Generative AI Leader Professional Certificate Github:https://github.com/droy2021/

Contact this candidate