Data Scientist

Insight Global’s client is hiring for Staff/Senior/Principal level Data Scientists to join their team focused in either time series forecasting or GenAi. Their team collaborates closely with Finance teams to enhance financial planning and strategic decision-making through cutting-edge data-driven solutions. They specialize in a range of initiatives that provide actionable insights into trends and patterns and leverage Generative AI (Genai) to produce concise, insightful summaries that empower decision-makers. By integrating these innovative approaches, we strive to drive efficiency, accuracy, and impactful outcomes in financial operations., * Lead the design, development, testing, and global deployment of large-scale time series forecasting models (including Regression models and state of the art time series specific models for example N-BEAST, PatchTST) to support complex retail and e-commerce hierarchies. Introduce causal modeling approaches to conduct impact analysis for future forecast.

• Continuously enhance forecasting strategies by incorporating advanced machine learning architectures, including RNNs (sequence modeling), CNNs (temporal feature extraction), and Attention-based mechanisms to improve accuracy, scalability, and robustness in time series forecasting.
• Advance causal modeling frameworks to quantify event impacts and integrate causal insights into forward-looking forecasts.
• Build and maintain experimentation pipelines (A/B testing, quasi-experiments, multi-armed bandits) for evaluating causal impacts of interventions.
• Mentor junior scientists, review research and production code, and ensure reproducibility and scalability in pipelines.
• Collaborate with engineering to implement forecasting + optimization systems in production (Airflow, Astronomer, Spark/Ray).
• Act as technical lead on multiple projects, balancing research rigor with business delivery.

• Strong foundation in Causal Inference, Statistical Analysis, and advanced Machine Learning methods
• Hands-on experience with a wide range of ML techniques, with a deep understanding of their advantages and limitations across different scenarios.
• Ability to integrate statistical expertise with machine-learning methods to maximize the value and interpretability of ML solutions.
• Proficiency in Python, SQL, PyTorch, Spark/Ray, and stats/econometrics libraries.
• Experience deploying ML systems at scale on cloud platforms (GCP/Azure).