Data Scientist

About the Company

Coromandel International Limited
is a leading Indian agrichemical company, part of the Murugappa Group and a subsidiary of EID Parry (owner of approximately 56–63%) Wikipedia+2Wikipedia+2.

Founded in the early 1960s (as Coromandel Fertilisers), the company is currently headquartered in Chennai with its registered office in Hyderabad Wikipedia.

They are one of India's largest private-sector producers of phosphatic fertilizers and the world's largest manufacturer of neem-based bio-pesticides CoromandelWikipedia. Additionally, they lead the market in organic fertilizers and operate the country's largest agri-retail chain, with 900+ stores serving over 2 crore farmers CoromandelWikipedia

About the Role

The Data Scientist is responsible for building advanced analytical models and AI/ML solutions that drive actionable insights, automate decision-making, and enable business transformation. The role requires strong problem-solving capabilities, proficiency in statistical and machine learning techniques, and the ability to collaborate with cross-functional teams to embed data-driven decision-making across business functions. The Data Scientist will manage the entire lifecycle of model development — from problem definition → data acquisition → model development → evaluation → deployment and monitoring. The role also contributes to the development of reusable assets, AI accelerators, and model governance standards across the organization.

Responsibilities

• Problem Identification & Scoping
• Work closely with business stakeholders to understand key challenges and opportunities
• Define clear analytical objectives and translate them into data science problems
• Identify feasibility based on data availability and technical constraints
• Data Preparation & Exploration
• Perform Data acquisition from structured and unstructured sources
• Conduct exploratory data analysis, feature engineering, and hypothesis testing
• Collaborate with data engineering teams to ensure reliable data pipelines
• Model Deployment and Monitoring
• Deploy models into production environments using CI/CD pipelines or APIs
• Collaborate with DevOps and IT teams for integration into enterprise systems
• Monitor model performance, decay, and ensure periodic retraining
• Business Impact & Value Realization
• Translate model outputs into business-friendly insights and decision aids
• Quantify impact through cost savings, revenue lift, efficiency gains, etc.
• Present findings to business and leadership teams in a compelling manner
• Collaboration and Mentorship
• Partner with Business Analysts, Domain SMEs, and Data Engineers on solution development
• Mentor junior data scientists and analysts in techniques and tools
• Contribute to AI/ML knowledge base, reusable codes, and best practices
• Governance & Compliance
• Ensure all models adhere to internal governance frameworks and regulatory norms
• Document models for reproducibility and auditability
• Work with IT Security to ensure data privacy and model security

Qualifications

Technical graduate (Engineering degree) or Graduate in Statistics, Applied Mathematics, Data Science, or a related quantitative field.

Required Skills

• Programming: Proficiency in languages like Python (preferred) and R, as well as SQL for database interactions.
• Statistics and Mathematics: Strong foundation in statistical methods, probability, and linear algebra.
• Machine Learning: Knowledge of various algorithms and their applications in data analysis and prediction.
• ML/AI Frameworks: Scikit-learn, XGBoost, TensorFlow, Keras, PyTorch.
• Data Tools: Pandas, NumPy, Spark, Databricks.
• Visualization: Power BI, Tableau, Plotly, Seaborn.
• ML Ops: MLflow, Azure ML, AWS SageMaker, Airflow.
• Databases: Understanding of database systems like SQL and NoSQL - example MS SQL Server, PostgreSQL, MongoDB, Snowflake.
• Big Data Technologies: Familiarity with tools like Hadoop and Spark for handling large datasets.
• Cloud: Experience with cloud platforms like AWS, Azure, or Google Cloud for data storage and processing - Azure (preferred), AWS, GCP.
• Version Control: Git, Azure DevOps.
• Other: Familiarity with NLP, time series forecasting, LLMs, or GenAI models.
• Data Security: Understanding of data protection and security measures.

Preferred Skills

• Experience: 7–10 years of experience in data science, machine learning, or advanced analytics.
• Proven track record in delivering business-impacting solutions using predictive modelling, optimization, or AI technologies.
• Experience in handling large datasets and working across diverse business domains.