Senior Data Scientist (Aviation & Supply Chain AI)

About the Role

We are a market-leading software company delivering the future of aircraft inventory planning. Aviation maintenance is a global industry constrained by manual, reactive processes and fragmented data. While the industry is ripe for transformation, mainstream systems fail to address the specific, stochastic reality of the "Repair to Reuse" model.

We are building the intelligent, autonomous supply chain for aviation MRO, and we are seeking a Senior Data Scientist to implement this mission. This is a prime position for a pragmatist who relishes complex, high-stakes problems.

You will be at the heart of defining how we turn institutional and market data and knowledge into proactive and automated execution. You will help define our hybrid-modular Agentic AI, which bridges the gap between deterministic logic and generative reasoning to automate the most critical decisions in the supply chain—keeping the aircraft flying and reducing costs.

You will work alongside our founders and leading domain experts to turn our proven RIOsys platform into the industry standard, helping global airlines move from reactive heavily manual processes to autonomous, event-driven resilience. If you are an experienced data scientist who wants to join a team to solve the most difficult supply chain problems in the world, and define the future of an industry, this role is for you.

Key Responsibilities

Applied Data Science & Modelling

• Develop practical data science and machine learning models to support forecasting, planning, optimisation, risk scoring, anomaly detection, and decision support.
• Analyse operational, transactional, historical, and planning data to identify patterns, trends, gaps, and useful business signals.
• Work with aerospace domain experts to understand inventory, demand, supply chain, repair, forecasting, and planning processes.
• Help improve the quality, reliability, and explainability of model-driven recommendations.
• Identify where machine learning is appropriate and where statistical methods, business rules, or deterministic logic are more suitable.

Forecasting & Decision Support

• Support the development and improvement of forecasting approaches for intermittent, slow-moving, variable, and high-value demand.
• Help evaluate forecast accuracy, bias, uncertainty, and business impact.
• Build new models for scoring and prioritisation methods to help users focus on the most important planning exceptions and risks.
• Support the development of data-driven recommendations that are clear, explainable, and useful to operational users.

AI-Enabled Product Features

• Contribute to the development of AI-assisted features using large language models, retrieval-augmented generation, and workflow automation.
• Help define how AI outputs should be grounded in trusted data, calculations, documentation, and system outputs.
• Support evaluation of AI-generated answers, explanations, and recommendations.
• Work with software developers to help turn prototypes and analytical outputs into usable product features.

Data Quality & Collaboration

• Work closely with the data engineering team to define data requirements for modelling, analytics, and AI features.
• Help identify data quality issues, gaps, inconsistencies, and limitations.
• Create model-ready datasets, features, and evaluation datasets.
• Collaborate with Java full-stack developers on model integration, APIs, data contracts, and product workflows.
• Communicate findings clearly to technical and non-technical stakeholders.

Current Technology Environment

The successful candidate will work with a non-exhaustive environment including:

• SQL databases, text based data snapshots and operational business data
• Historical demand, forecast, inventory, purchasing, repair, and planning data
• Python, SQL, pandas, NumPy, scikit-learn, statsmodels
• Jupyter notebooks or similar analytical environments
• Git
• Java-based SaaS application platforms
• Data pipelines maintained by the data engineering team
• Cloud-hosted production environments
• Emerging use of LLMs, RAG, and AI-assisted workflow automation

Required Skills & Experience

Essential

• 5+ years’ experience in applied data science, machine learning, advanced analytics, or a closely related role.
• Strong Python and SQL skills.
• Proven experience designing and deploying end-to-end, production-grade AI/ML systems
• Hands-on experience moving LLMs and RAG pipelines beyond prototypes into high-reliability, production-grade environments where output quality and explainability are non-negotiable.
• Strong understanding of data preparation, feature engineering, model evaluation, and validation.
• Experience working with messy, incomplete, or complex operational data.
• Ability to explain model outputs, assumptions, limitations, and uncertainty clearly.
• Experience supporting forecasting, classification, ranking, recommendation, anomaly detection, or decision-support use cases.
• Ability to work independently without requiring close data science supervision.
• Comfortable collaborating with software developers, data engineers, product stakeholders, and domain experts.
• Strong communication skills and a practical, outcome-focused approach.

Desirable

• Experience in aerospace, aviation, MRO, inventory optimisation, supply chain, logistics, manufacturing, or another complex operational domain.
• Experience with intermittent demand forecasting or slow-moving inventory.
• Experience with MLflow or similar experiment/model tracking tools.
• Experience working with Java-based enterprise software platforms.
• Familiarity with cloud platforms such as AWS, Azure, or GCP.
• Familiarity with SOC 2, ISO 27001, or similar security and compliance frameworks.

Personal Attributes

We are looking for someone who:

• Takes ownership of their work.
• Is organised, methodical, and analytical.
• Is pragmatic rather than academic.
• Can work independently while collaborating closely with others.
• Communicates clearly with both technical and business stakeholders.
• Is comfortable working with domain experts to understand complex business problems.
• Can challenge assumptions constructively.
• Understands the importance of explainability and trust in AI and data science.
• Enjoys solving ambiguous, real-world problems.