Senior Data Scientist – Process Analytics & Digital Twin

Job Title: Senior Data Scientist – Process Analytics & Digital Twin

Location: Remote

Job Type: Full Time

About Us

Infinite Uptime leverages advanced predictive maintenance, process data analytics, and digital twin technologies to deliver actionable insights that optimize industrial performance. Our platform powers intelligent, data-driven decisions across sectors like Cement, Steel, Paper, Fertilizers and FMCG, helping industries unlock efficiency, reduce downtime, and improve throughput with measurable impact.

Job Description

We are looking for an experienced Senior Data Scientist with deep expertise in industrial process data analytics, digital twin modeling, and cross-industry operational understanding. The ideal candidate will combine data science proficiency with the ability to understand and analyze complex process streams, identify Key Performance Indicators (KPIs) relevant to each industry, and deliver insights that enhance process throughput and efficiency.

You will collaborate with cross-functional teams including process engineers and domain experts to build scalable models and simulations that drive business outcomes.

Key Responsibilities

• Analyze real-time and historical process data streams to derive actionable insights and identify areas for process optimization.
• Develop data-driven digital twins and predictive models to simulate and monitor industrial systems.
• Understand end-to-end process workflows in industries such as cement (e.g., kilns, mills), steel (e.g., furnaces, rolling mills), paper (e.g., pulping, drying), and FMCG (e.g., packaging, filling lines).
• Translate domain knowledge into measurable KPIs and modeling objectives aligned with business goals.
• Design and implement machine learning and statistical models for anomaly detection, prediction, and optimization.
• Conduct feature engineering, root cause analysis, and data quality assessments on high-volume time-series datasets.
• Automate data workflows, monitor model performance, and iterate based on business feedback.
• Maintain well-documented analysis pipelines, test results, and insight reports.
• Collaborate with internal stakeholders to deploy models and support data-driven decision making.

Requirements

• 5+ years of hands-on experience in Data Science, with proven applications in process industries or manufacturing environments.
• Solid understanding of process engineering concepts and industrial KPIs across cement, steel, paper, or FMCG domains.
• Strong command of Python, including libraries like pandas, NumPy, Scikit-learn, TensorFlow/PyTorch.
• Proficiency with SQL and working with time-series data.
• Experience developing and deploying machine learning or statistical models in production.
• Familiarity with industrial data sources (e.g., SCADA, PLC, historians).
• Strong problem-solving and communication skills, especially in cross-functional environments.

Preferred Qualifications

• Experience building or contributing to digital twin architectures.
• Familiarity with MLOps pipelines, model versioning, and continuous integration tools.
• Exposure to optimization techniques (e.g., genetic algorithms, Bayesian optimization).
• Experience working with cloud platforms (AWS, Azure, GCP) and Big Data tools (e.g., Spark).
• Understanding of industrial communication protocols (OPC UA, Modbus) and control systems.

Why Join Us?

• Contribute to high-impact data science initiatives that directly improve industrial operations.
• Collaborate with a forward-thinking team at the intersection of AI, IoT, and industrial engineering.
• Be part of a mission-driven company transforming global manufacturing through innovation.