Lead Data Scientist

Company Description
Saatvik Agro is the agro-ingredient unit of the Saatvik Group, specializing in high-quality maize-based ingredients used in food, nutrition, animal feed, and industrial applications. The organization focuses on purity and scientific rigor, converting responsibly sourced maize into functional and reliable ingredient solutions. Its products are designed to meet the evolving needs of modern manufacturers who demand consistency, performance, and safety. Guided by the belief that better ingredients create better outcomes, Saatvik Agro aims to support customers in delivering superior products to their markets.
Role Description
We are looking for a Lead Data Scientist for a full-time, on-site opportunity based in Morena, Madhya Pradesh, India.
The role is suitable for experienced data and analytics professionals with backgrounds in Data Science, Machine Learning, Artificial Intelligence, Predictive Analytics, Statistical Modeling, Forecasting, Experimentation, MLOps, and Business Analytics.
The Lead Data Scientist will work closely with data, software, IT, production, operations, supply chain, finance, sales, quality, and leadership teams to identify high-impact analytical opportunities, lead data-science initiatives, build advanced models, and translate complex data into actionable business decisions.
Qualifications
B.E. / B.Tech / B.Sc. / MCA / M.Sc. / M.Tech in Data Science, Computer Science, Artificial Intelligence, Machine Learning, Statistics, Mathematics, Economics, Engineering, or a related quantitative discipline.
Candidates with 4+ years of relevant experience in data science, machine learning, advanced analytics, AI, predictive modeling, or related roles are encouraged to apply.
Candidates currently working as Senior Data Scientist, Lead Data Scientist, Machine Learning Engineer, Senior Machine Learning Engineer, Applied Scientist, AI Engineer, Analytics Lead, Senior Data Analyst, or Data Science Consultant are encouraged to apply.
Candidates from IT services, SaaS, product companies, analytics, consulting, fintech, e-commerce, FMCG, manufacturing, logistics, supply chain, telecom, or other industries are welcome.
Strong proficiency in Python and SQL.
Strong understanding of statistics, probability, hypothesis testing, regression, experimentation, and quantitative analysis.
Strong knowledge of machine learning algorithms, feature engineering, model validation, evaluation metrics, and hyperparameter optimization.
Experience with libraries and frameworks such as Pandas, NumPy, Scikit-learn, XGBoost, LightGBM, TensorFlow, PyTorch, or similar tools.
Experience with time-series forecasting, predictive modeling, optimization, anomaly detection, or recommendation systems will be beneficial.
Strong ability to work with large, complex, and imperfect datasets.
Experience with SQL databases, data warehouses, data lakes, and enterprise data platforms.
Exposure to AWS, Azure, Google Cloud, Databricks, Snowflake, BigQuery, Redshift, or similar technologies will be beneficial.
Familiarity with MLflow, Airflow, Docker, APIs, CI/CD, model serving, or MLOps tools will be an advantage.
Exposure to NLP, computer vision, deep learning, generative AI, LLMs, or advanced AI applications will be beneficial but is not mandatory.
Experience with visualization tools such as Power BI, Tableau, Looker, or similar platforms will be advantageous.
Understanding of data quality, governance, privacy, model monitoring, and responsible AI principles.
Experience mentoring junior data professionals or leading analytical projects will be highly beneficial.
Strong business understanding and ability to connect analytical work with measurable outcomes.
Strong analytical, mathematical, logical, and problem-solving abilities.
Good presentation, communication, documentation, and stakeholder-management skills.
Ability to explain complex analytical concepts clearly to business and technical teams.
Willingness to work in an on-site environment.
Strong ownership mindset and ability to independently lead complex data-science projects from problem definition through deployment and business adoption.

Work arrangement
No