Data Scientist - Supply Chain Analytics

• Proficiency in AWS services, AI/ML modeling, Data modeling, data engineering, data analytics, tableau and Azure devops for project management.
• Strong Proficiency in Python and/or other programming language
• Should perform data analysis detailing the trends and bottlenecks in the MRO process and part supply chain.
• Experience with unstructured data processing and NLP
• Experience with generative-ai and agentic AI frameworks
• Experience in applying analytics in business problems
• Should develop, test, and validate the various machine learning models to predict for issues for future operations based on the historical data analysis from past operations.
• Development of data models using AWS services (e.g., Sagemaker, Glue, Lambda, S3, Redshift).
• Publish accuracy, precision, recall, F1-Score, MSE, R-squared etc. for the models
• Configuration of monitoring, logging, and alerting mechanisms (e.g., Cloud Watch, SNS).
• Develop modular code that passes the static and dynamic Info-sec vulnerability scans
• Deploy automation to change the solution to be automated.
  
  E.g. Deployments, Certificate updates, Infrastructure changes, code changes, failure notifications etc.
• Document Runbook details of the above-mentioned models along with all the cloud and code assets created by the team.
• Conduct testing and validation activities for data and developed models.

Strong grasp of supply chain processes, including inventory management, procurement and logistics.

• Collaborate with stakeholders to understand the current MRO process flow
• Gather actionable insights into the process flow and supply chain for the maintenance, repair, and overhaul operations
• Analyze data around these processes and identify places where they can be optimized to provide quality services with greater speed.
• Incorporated models into a broader application which will drive actions by business and operations stakeholders
• Modeling & Advanced Analytics
• Algorithmic framework to process financial data and generate structured reports
• Validate accuracy of the generated reports against human written reports

• Algorithmic framework to process and derive insights from unstructured constraint notes data
• Identify data trends such as last time buyer updated the record and other information to identify potentially stale, complete , cancelled and/or erroneous records
• Development of the project plan with key milestones and project deliverables
• Report out to stakeholders highlighting achievements, risks, and future work.
• Develop, test, and validate the various machine learning models
• Follow the Agile standard for the development of the requested proposal.
• Bring best practices, standards, and innovative ideas for Data Science, process, architecture, and design.
• Requirements gathering and architecture design.
• Development of data models using AWS services (e.g., Sagemaker, Glue, Lambda, S3, Redshift).
• Make data model outputs available for consumption, applications, and self-service.
• Build models that are performant and optimized for cloud expenses.
• Implement security, governance, monitoring, alerting, and job orchestration as defined by ARB.
• Conduct reviews along with frequent communication for stakeholders.
• Deployment of ingestion pipelines into dev, pre, and production environments.
• Configuration of monitoring, logging, and alerting mechanisms (e.g., Cloud Watch, SNS).
• Unit testing, integration testing, functional, and non-functional testing.
• Handover documentation with a training session.

• Exceptional communication to bridge technical and non-technical teams.
• Strong analytical and problem-solving skills.
• Stakeholder management and cross-functional collaboration.

Please note – Centraprise is an equal opportunity employer. Applicants must be authorized to work in the U.S.

U.S. Citizens and Green Card holders are strongly encouraged to apply.