Description : Data Scientist (Manufacturing & MLOps)

Experience : 4+ Years

Location : Pune

Notice Period : 30 Days

Role Summary :

We are seeking a highly technical Data Scientist to join our manufacturing digital transformation team.

In this role, you will be responsible for developing and deploying advanced predictive models that drive operational efficiency on the manufacturing shopfloor.

You will leverage Core Data Science principles, including Regression and Statistical Analysis, to solve complex industrial challenges.

A significant portion of this role involves MLOps, where you will architect and manage the end-to-end lifecycle of machine learning modelsfrom initial Predictive Modeling to large-scale Deployment on cloud platforms like AWS, Azure, or GCP.

This position requires a professional who can translate raw industrial data into actionable insights, ensuring that AI-driven solutions are both robust and scalable within a high-concurrency manufacturing environment.

Responsibilities :

- Core Data Science Engineering : Design and implement sophisticated machine learning models using Regression, classification, and clustering techniques tailored for manufacturing data.

- Predictive Modeling : Develop high-accuracy predictive models to forecast equipment failure, optimize supply chain throughput, and improve product quality metrics.

- MLOps & Deployment : Own the end-to-end machine learning lifecycle, establishing robust MLOps pipelines for automated model training, versioning, and Deployment.

- Statistical Analysis : Conduct deep-dive Statistical Analysis on shopfloor data to identify patterns, anomalies, and root causes of production inefficiencies.

- Cloud Architecture Integration : Architect and manage data science workloads across multi-cloud environments, including AWS, Azure, and GCP.

- Manufacturing Domain Alignment : Partner with shopfloor engineers to understand physical processes and translate them into mathematical models that drive Digital Transformation.

- Model Performance Governance : Establish monitoring frameworks to track model drift and performance post-deployment, ensuring long-term reliability of AI assets.

- Data Pipeline Orchestration : Collaborate with data engineers to design scalable pipelines that ingest and process high-velocity data from sensors and industrial IoT devices.

- Technical Stakeholder Communication : Clearly articulate complex mathematical findings and model behaviors to both technical teams and manufacturing leadership.

- Innovation & Research : Stay at the forefront of AI research to identify new algorithms or MLOps tools that can further optimize manufacturing workflows.

Technical Requirements :

- Domain Expertise : 4+ years of hands-on experience in Data Science specifically within the Manufacturing domain.

- Mathematical Foundation : Expert-level proficiency in Statistical Analysis, Regression models, and Predictive Modeling.

- MLOps Proficiency : Demonstrated experience in building and maintaining MLOps pipelines for industrial-scale Deployment.

- Cloud Mastery : Technical proficiency in deploying machine learning solutions on AWS, Azure, or GCP.

- Programming Skills : Advanced skills in Python or R, along with familiarity with data science libraries (e.g., Scikit-learn, TensorFlow, PyTorch).

- Industrial Data Knowledge : Familiarity with time-series data and data structures typical of manufacturing execution systems (MES) and PLCs.

Preferred Skills :

- Deep Learning : Experience applying neural networks to industrial image recognition or complex sensor-fusion tasks.

- Edge AI : Knowledge of deploying lightweight models directly onto Edge Devices for real-time shopfloor inference.

- Visualization Mastery : Proficiency in tools like Tableau, Power BI, or Plotly to create intuitive dashboards for manufacturing stakeholders.

- Advanced Certifications : Professional certifications in Cloud Machine Learning (AWS/Azure/GCP) or MLOps engineering.

- Problem Solving : Exceptional ability to deconstruct vague manufacturing problems into specific, solvable data science hypotheses