Data Scientist - Manufacturing Analytics

Must-Have Skills / Requirements

• 6+ years of experience in Data Science / Advanced Analytics
• Hands-on experience in manufacturing / industrial / plant environments
• Strong working knowledge of Seeq (industrial analytics platform) for time-series analysis, including both Seeq Workbench and Data Lab (using the seeq spy library).

Proficiency in Python (Pandas, NumPy, Scikit-learn) and SQL

Strong understanding of:

Machine Learning (regression, anomaly detection, predictive models)

Statistical modeling and hypothesis-driven analysis

Time-series / sensor data analytics

Experience building and deploying predictive models for:

Predictive maintenance

• Process optimization
• Quality and yield improvement
• Ability to work with sensor data, process data, and operational datasets
• Strong analytical thinking, troubleshooting, and root-cause analysis capability
• Good-to-Have Skills
• Experience in industries such as:

Oil & Gas, Chemicals, Manufacturing

Knowledge of MLOps (model deployment, monitoring, pipelines)

Exposure to optimization techniques for industrial processes

Exposure to cloud platforms (Azure / AWS / GCP)

Familiarity with data visualization tools, real-time / streaming data analytics, data engineering (ETL / data pipelines / data lakes)

Roles & Responsibilities

Analyze manufacturing plant and process data to identify patterns, anomalies, and optimization opportunities

Use Seeq platform for:

Time-series analysis

• Root cause investigation
• Process monitoring and visualization
• Develop and deploy machine learning models for:

Predictive maintenance

• Process efficiency improvement
• Quality / yield optimization
• Work closely with plant, engineering, and operations teams to understand real-world process issues
• Translate business and operational challenges into data science solutions
• Build and maintain data pipelines, analytical datasets, and workflows
• Monitor, evaluate, and continuously improve model performance in production
• Present actionable insights through dashboards, reports, and stakeholder discussions
• Ensure data quality, reliability, and governance across manufacturing data sources
• Drive adoption of data-driven decision-making across plant operations