Data Scientist

Job Responsibilities:

• Design and implement anomaly and pattern detection algorithms to identify irregular transaction behaviors, synthetic activities, and coordinated anomalies in real-time.
• Develop predictive analytics models to forecast user engagement trends, platform utilization, potential churn, and high-value customer segments.
• Automate manual data monitoring processes by building Python-based workflows and SQL-driven alert systems to detect and flag outliers instantly.
  
• Conduct in-depth data forensics investigations on complex and unstructured log data to determine root causes of discrepancies or unusual system activity.
• Collaborate with engineering teams to optimize data pipelines and structures (e.g., ClickHouse, AWS environments) to ensure high-performance model execution on live datasets.
• Write scalable, production-ready code and ensure model reliability, efficiency, and maintainability.
• Continuously refine analytical models and detection mechanisms to improve accuracy and reduce false positives.
  
  

Job Requirements:

• Bachelors Degree in Data Science, Computer Science, Statistics, Mathematics, or a related quantitative field.
• Minimum 1–2 years of hands-on experience in data science, analytics, or a data-intensive engineering role.
• Proficient in Python, with experience using libraries such as Pandas, NumPy, and Scikit-learn for data manipulation, analysis, and modeling.
• Possessed SQL skills, including complex joins, window functions, CTEs, and large-scale data transformation.
• Foundation in statistics and machine learning concepts, including regression, classification, clustering, and outlier detection techniques.
• Experience with automation scripting and workflow optimization is required.
• Familiarity with containerization tools (e.g., Docker), high-performance databases (e.g., ClickHouse), AWS environments, or local AI models is an added advantage.
• Portfolio or GitHub repository showcasing relevant projects (data cleaning, ML models, automation scripts) is preferred.