Job Description
<p>- We are building Saulikh, a platform transforming agri-trade with data science and AI.<br/><br/>- Our goal is to bring trust, transparency, and intelligence to commodity trading at scale.<br/><br/> Role Overview:<br/><br/>- We are seeking a Data Scientist to lead data-driven initiatives across trade, pricing, risk, and logistics.<br/><br/>- The role involves working with real-world datasets, building dashboards, applying ML models, and assisting in the development of prototypes for trust scoring, fraud detection, and forecasting.<br/><br/> Key Responsibilities:<br/><br/>- Collect, clean, and preprocess financial, transactional, and behavioral datasets from multiple sources.<br/><br/>- Design and implement trust/credit scoring algorithms that assess buyer/seller reliability and default risk.<br/><br/>- Engineer features from trade history, payment timeliness, disputes, cancellations, and external market data.<br/><br/>- Apply statistical models and machine learning techniques (logistic regression, random forests, gradient boosting, neural networks) to predict trustworthiness.<br/><br/>- Develop scoring frameworks normalized to a range (e.
, 0-1000), similar to CIBIL standards.<br/><br/>- Validate and back-test models against historical data to ensure accuracy, fairness, and stability.<br/><br/>- Build monitoring pipelines to track score performance, drift, and anomalies in real time.<br/><br/>- Work with business and product teams to ensure scores align with practical trade and risk management requirements.<br/><br/>- Document methodologies and communicate insights to technical and non-technical stakeholders.<br/><br/>- Requirements - Bachelor's or Master's degree in Computer Science, Statistics, Mathematics, Economics, or a related field.<br/><br/>- 2-5 years of experience as a Data Scientist, preferably in credit scoring, risk modeling, or fraud detection.<br/><br/>- Strong proficiency in Python (pandas, numpy, scikit-learn, statsmodels) or R.<br/><br/>- Experience with machine learning algorithms such as logistic regression, decision trees, random forests, gradient boosting (XGBoost/LightGBM), and neural networks.<br/><br/>- Strong SQL skills for handling large datasets; experience with data pipelines and API integrations.<br/><br/>- Domain knowledge of credit scoring principles, risk assessment, and regulatory considerations.<br/></p> (ref:iimjobs.com)