Data Scientist

Build Predictive Weather Models: You will design, train, and deploy machine learning and spatio-temporal models to integrate weather feeds with client sales data to predicting demand, optimizing forecasts, and quantifying operational risk.

Derive Actionable Insights: You will conduct end-to-end exploratory analysis on complex meteorological datasets to uncover high-value patterns and translate probabilistic trends into strategic recommendations.

Drive B2B & Commercial Growth: You will partner with Sales, Marketing, and Customer Support to build analytics solutions for B2B initiatives.

Optimize ML Performance: You will leverage distributed frameworks (e.g., PySpark, Dask, Ray) and modern ML stacks (Scikit-learn, PyTorch/TensorFlow, LLMs) to improve model speed, scale inference pipelines, and lower compute costs.

Own the Model Lifecycle: Take responsibility for the full end-to-end lifecycle, including testing, deployment, and ongoing monitoring to ensure production-grade stability and reliability.

Technical documentation: Actively document model architectures, data lineage, and decision logic to ensure reproducibility, facilitate peer review, and maintain long-term institutional knowledge.

Cross-Functional Collaboration: You will partner closely with Data Engineers, Product Managers, and Revenue leaders to embed predictive algorithms into live APIs and deliver scalable data products that solve real-world enterprise problems.

Degree in a STEM discipline (Data Science, Statistics, Computer Science, or a related quantitative field); a Master’s or PhD is preferred but not required. 

3+ years of data science experience specializing in B2B environments, with expertise in spatio-temporal modeling, time-series forecasting, and weather data intelligence. 

High proficiency in Google BigQuery (SQL, window functions, query optimization, and large-scale data manipulation).

Advanced expertise in Python for statistical modeling, data science, and graphical visualization (e.g., Matplotlib, Seaborn, or Plotly), with hands-on experience using core ML libraries including NumPy, SciPy, Scikit-learn, and TensorFlow or PyTorch. 

Experience working with distributed computing frameworks (e.g., Apache Spark) to process large-scale datasets. 

Strong communication skills, including the ability to explain complex ideas to an audience with a non-technical background 

Proven experience developing and deploying Deep Learning models in industry or research environments. 

Familiarity with deploying Large Language Models (LLMs) or retrieval-augmented generation (RAG) pipelines for automated reporting, intelligent customer support routing, or unstructured data processing. 

Experience scaling models across large datasets using distributed processing frameworks.