We are seeking a seasoned Advanced Data Scientist Consultant with deep expertise in statistical forecasting, time-series modelling, and machine learning to join a high-impact analytics. The consultant will lead the end-to-end design and deployment of forecasting and predictive modelling solutions that drive critical business decisions across demand planning, risk assessment, and operational optimisation.
The ideal candidate is a self-driven problem-solver who can translate complex analytical findings into actionable recommendations, collaborate with cross-functional stakeholders, and deliver production-ready models within tight timelines.
Relevant Experience Desired
6 to 8 Years
Key Responsibilities
- Design, build, and validate advanced forecasting models (time-series, causal, hybrid) for demand, revenue, risk, and operational KPIs.
- Develop and optimize machine learning models including regression, classification, clustering, and ensemble methods tailored to business forecasting needs.
- Apply statistical methods such as ARIMA, SARIMA, Prophet, LSTM, XGBoost, and Bayesian models to solve complex forecasting challenges.
- Conduct feature engineering, selection, and hyperparameter tuning to improve model accuracy and generalisability.
- Perform model backtesting, validation, and error analysis (MAPE, RMSE, MAE) to ensure forecast reliability.
- Extract, clean, transform, and integrate large and complex datasets from multiple sources (SQL databases, APIs, flat files, cloud storage).
- Conduct exploratory data analysis (EDA) to surface patterns, anomalies, and actionable business insights.
- Build and maintain scalable, reproducible data pipelines for model training, scoring, and monitoring.
Delivery & Collaboration
Required Skills & Qualifications
Must-Have
- 6–8 years of hands‑on experience in data science with a strong focus on forecasting, time‑series analysis, and predictive modelling.
- Proficiency in Python (pandas, NumPy, scikit‑learn, statsmodels, Prophet, TensorFlow/PyTorch) and/or R.
- Strong command of statistical and ML techniques: ARIMA/SARIMA, Exponential Smoothing, XGBoost, LightGBM, LSTM/RNN, Random Forest.
- Hands‑on SQL experience for data extraction and manipulation from relational databases.
- Proven track record of deploying forecasting models in production environments.
- Experience with model evaluation metrics (MAPE, RMSE, MAE, WAPE) and A/B testing frameworks.
- Strong communication skills — ability to simplify complex modelling concepts for non‑technical audiences.
Good to Have
- Experience with cloud platforms: AWS (SageMaker, S3), Azure (ML Studio), or GCP (Vertex AI).
- Familiarity with MLOps tools: MLflow, DVC, Airflow, Kubeflow for pipeline orchestration and model versioning.
- Knowledge of Spark or PySpark for distributed computing on large‑scale datasets.
- Experience with NLP or generative AI techniques applied to structured business data.
- Exposure to BI and visualisation tools: Power BI, Tableau, or Looker for presenting model outputs.
Education
- BTech / B.E. / B.Sc. in Computer Science, Statistics, Mathematics, Engineering, or a related quantitative field — Required.
- MTech / M.Sc. / MBA (Analytics/Data Science) or equivalent postgraduate qualification — Preferred.
- Certifications in Data Science, ML, or Cloud (e.g., AWS Certified ML Specialty, Google Professional Data Engineer, Coursera/edX specialisations) — Advantageous.
About Us
Terra TCC is a Technology & Sustainability company offering services in Software, Environment Consulting, and Staff Augmentation to top‑notch clients. We continuously strive to help companies find the right technology, the right services and the right talent for their needs. Learn more at www.terratcc.com
Any information that is shared with us, shall be retained as per company's data privacy policy. In case you wish to revise, modify or delete any of the submitted information, please write back to us. See contact details on https://www.terratcc.com/get-in-touch/