About Kanan
Kanan is building AI software to help manufacturers and financial institutions understand supply chains, assess risk, and make informed decisions. We are bringing together a founding team across AI research, engineering, and data science.
About the role
As a Founding Data Scientist, you will develop the quantitative methods behind Kanan’s supply-chain and risk capabilities. Your work will connect operational data with practical questions about production, delivery, and the financial constraints that affect business performance.
You will work with manufacturers, business stakeholders, and the founding team to understand how processes operate and which outcomes can be measured. You will build models, test their assumptions, and explain what the evidence supports. Working with incomplete data is part of the role, as is identifying which additional information would make an analysis more useful. You will document assumptions and model behaviour so that colleagues can review the analysis and understand when a result needs further investigation.
Responsibilities
- Analyse supplier, production, order, and financial data to identify patterns, constraints, and sources of operational risk.
- Model lead times, capacity constraints, supplier dependencies, and delivery risk, reflecting how real production and supply-chain processes work.
- Use statistical modelling, simulation, and optimization to assess scenarios and understand how different assumptions affect the results.
- Evaluate how supply disruptions, changing input costs, and financial constraints affect production and fulfilment in specific business situations.
- Validate models against observed outcomes, assess their reliability, and communicate uncertainty and limitations clearly to technical and business audiences.
- Work with operators and engineers to define useful measurements, improve data quality, and turn validated analysis into product capabilities.
Required qualifications
- Applied experience in supply-chain data science, operations research, industrial engineering, or quantitative risk, with evidence of solving operational problems.
- Strong Python, SQL, probability, and statistics, and the ability to build and explain your own analytical models.
- Experience working with incomplete operational data, testing assumptions, and validating models against outcomes rather than relying only on historical fit.
- Ability to connect analytical findings to business decisions and learn directly from the people responsible for production, procurement, or finance.
Preferred experience
- Experience in manufacturing, logistics, working-capital analysis, or financial risk involving the operations of a business.
- Experience with stochastic modelling, sensitivity analysis, or simulation of production and supply-chain systems under uncertainty.