> Markdown version of [/jobs/ext/3614106-senior-data-scientist-ml-engineer-forecasting-nda](https://www.wearedevelopers.com/jobs/ext/3614106-senior-data-scientist-ml-engineer-forecasting-nda). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Senior Data Scientist / ML Engineer (Forecasting) | NDA

- **Company:** Offshore Software Development and Product Studio
- **Location:** Nottingham, UK
- **Experience:** Expert
- **Salary:** £89,549.0
- **Contract:** Permanent contract
- **Skills:** Amazon Web Services, Microsoft Azure, Python (Programming Language), Machine Learning, NumPy, Standard Sql, Cloud Platform System, Pytorch, Prophet, Retrieval-Augmented Generation, Model Validation, Git, Pandas, Pyspark, Scikit Learn, Xgboost, Performance Monitor, Weaviate, Milvus, DeepEval, Evaluation of Large Language Models, Software Version Control, Recurrent Neural Networks, Databricks
- **Published:** October 8, 2026
- **Apply:** https://www.adzuna.co.uk/jobs/details/5918687347

## About the Role

* 4+ years of commercial experience in Data Science / Machine Learning
 * Hands-on experience with:
 + Databricks
 + Notebooks
 + PySpark
 + Workflows
 + Deployment through Asset Bundles
 * Proven experience building, deploying, and maintaining production ML solutions
 * Broad experience across multiple ML domains, including:
 + Forecasting / Time-Series Modelling
 + Regression
 + Classification
 + Gradient Boosting models (e.g. XGBoost, LightGBM)
 * Strong Python skills (Pandas, NumPy, scikit-learn, PyTorch)
 * Experience with model evaluation, performance monitoring, and accuracy metrics
 * Version control (Git)
 * Experience working with cloud environments (Azure preferred, AWS/GCP also considered)
 * SQL
 * Fluent English

 * Retail or similar consumer-facing industry experience
 * Azure DevOps:
 + Repos
 + Boards
 + Pipelines
 * Experience with Databricks model training and inference workflows
 * Databricks Apps and Lakebase
 * Experience with RAG pipelines
 * Experience with vector databases (Weaviate, Milvus)
 * Familiarity with LLM evaluation frameworks (e.g. DeepEval)

 * Strong sense of ownership and accountability
 * Strong stakeholder management skills
 * Proactive attitude and ability to work independently
 * Clear and confident communication with both tech and non-tech stakeholders
 * Comfortable working in ambiguity and helping define requirements
 * Strategic thinking and focus on business impact
 * Team player

## Description

The project focuses on developing a forecasting solution for a large healthcare network.
It uses historical clinic and marketing data to predict clinic usage and staffing needs, helping optimize scheduling and resource allocation.
The goal is to build a scalable, data-driven platform that improves operational efficiency.

 * Design, train, and deploy ML models for time-series forecasting and related data tasks
 * Build and maintain data pipelines using cloud-native tools (AWS, GCP, or Azure)
 * Develop and optimize forecasting models (Prophet, ARIMA, LSTM, TimeGPT)
 * Collaborate with data, product, and cloud engineers to deliver reliable, scalable solutions
 * Participate in different stages of the project lifecycle - from discovery and PoC to production deployment, presenting your work to stakeholders
 * Work closely with business stakeholders and SMEs to gather requirements, shape solutions, and drive project discovery
 * Communicate modelling approaches, assumptions, and results to both technical and non-technical audiences