Data Science Lead

This role is heavily focused on econometric modeling, time series analysis, and causal inference, with applications in forecasting, pricing, and customer behavior analytics. The ideal candidate brings deep expertise in statistical modeling and is comfortable working with large-scale data environments.

Key Responsibilities

• Lead development of time series forecasting models (ARIMA, VAR, state-space models, etc.) for business-critical use cases. 


• Apply econometric techniques such as WLS, panel data models, and causal inference methods to solve real-world business problems. 


• Design and implement Bayesian models and probabilistic frameworks for uncertainty estimation and decision-making. 


• Utilize Markov chains and stochastic processes for modeling sequential or behavioral data. 


• Translate business problems into robust analytical frameworks and deliver actionable insights. 


• Work with large datasets using Databricks 


• Collaborate with stakeholders across business and technical teams to ensure model relevance and impact. 


• Mentor junior team members and drive best practices in statistical modeling and experimentation.

Must-Have Qualifications

• Strong foundation in econometrics and time series analysis (this is critical for the role). 


• Hands-on experience with: 
  
  
  
  • Time series models (ARIMA, SARIMA, VAR, forecasting techniques) 
  
  
  • Econometric methods (WLS, regression diagnostics, panel data models) 
  
  
  • Causal inference (A/B testing, quasi-experimental methods) 
  
  
  • Bayesian statistics and probabilistic modeling 
  
  
  • Markov chains or stochastic modeling 
  
  


• Proficiency in Python along with SQL. 


• Experience working with Databricks or similar big data platforms. 


• Ability to clearly communicate complex statistical concepts to non-technical stakeholders.

Secondary / Good-to-Have Skills (General Data Science)

• Experience with machine learning models (classification, regression, tree-based models, etc.) 


• Familiarity with feature engineering, model validation, and performance tuning 


• Exposure to ML pipelines and MLOps concepts