Hiring nowSupply chain, logistics and mobility analytics

Supply Chain AI Scientist

Also called Supply Chain ML Scientist

A Supply Chain AI Scientist builds models of demand, supply and disruption that planners can act on. The work helps a company hold the right stock, meet service promises and absorb shocks without overspending.

What they do

They model how demand, lead times, capacity and disruption behave, then turn those models into planning decisions. One week might go on cleaning order and shipment data and building a forecast with honest uncertainty. The next might go on feeding that forecast into an optimisation that sets stock levels or routes. They test models against what actually happened, using rolling validation rather than a single split. They sit with planners and operations teams to learn which constraints are real and which are habit. They also write down what the model assumes, so others can trust it.

What a strong hire delivers

In the first months, a strong hire gets a working planning model in front of the people who use it. They set up rolling validation so the team can see how forecasts and decisions would have performed on past periods. They agree the measures that matter with operations, such as service levels, inventory outcomes and forecast error. They leave behind data pipelines that run reliably and a clear view of where uncertainty is largest.

How you can tell they are good

Ask them to walk through one planning model they built, end to end. Listen for how they handled uncertainty, not just point forecasts. Ask how they validated it over time and what they changed after it was wrong. A strong candidate talks about planner behaviour, constraints and cost of error. Be wary of anyone who only quotes accuracy scores or reaches for complex models before checking the data.

Why it is hard to fill

The title is new and people arrive from several directions, so job titles rarely match. Most candidates are strong in one area: forecasting, optimisation or data engineering. Few combine all three with real operational sense. Many data scientists have never had to live with a planning decision they recommended. Many operations research people have had little exposure to modern forecasting. From a recruiter's view, the search is about judging depth, not matching keywords.

Where to find them

Look first at supply-chain analytics teams in retailers, manufacturers and distributors. Operations research groups and transport engineering departments are strong sources. Logistics technology companies, planning software firms and freight or mobility operators also employ people doing this work. Titles often read as demand planner with modelling skills, operations research analyst, forecasting scientist, or supply chain data scientist. Some come from consultancies where they built planning tools for clients.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for a Supply Chain AI Scientist

  1. Describe a demand or supply model you built that planners actually used. What changed in their decisions?

    A strong answer names the decision, the users and the measured effect on service or inventory. It covers how trust was earned. Worry if the answer stops at model accuracy or the model never left a notebook.

  2. How do you validate a forecast for planning purposes, and why not a random train and test split?

    They should explain rolling or time-ordered validation, leakage risks and evaluating over several periods. Good answers connect error to decision cost. Worry if they split randomly or only report one aggregate error figure.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are looking for a Supply Chain AI Scientist to build the models that help us plan demand, supply and disruption. You will work closely with operations and planning teams, turning data into decisions they can trust and act on. The work is hands on, from data pipelines through to validated planning models.

What you will do

  • Build forecasting models for demand, supply and lead times, with clear measures of uncertainty
  • Develop planning and optimisation models that respect real operational constraints
  • Set up rolling validation to test models against past outcomes
  • Build and maintain the data pipelines those models depend on
  • Model disruption scenarios and show their likely effect on service and inventory
  • Work with planners to define success measures and review results
  • Document assumptions and limits so others can use the models safely

What you will bring

  • Shipped at least one planning or forecasting model that people used in real decisions
  • Strong grounding in probability, statistics and time-series modelling
  • Practical experience with optimisation or operations research methods
  • Able to build reliable data pipelines in a production setting
  • Evidence of validating models over time, not only on a single split
  • Clear communicator with non-technical operations colleagues

Nice to have

  • Experience with routing or transport network problems
  • Familiarity with logistics or warehouse systems
  • Experience modelling disruption or scenario planning

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Optimisation and operations researchAdvancedChoose actions subject to objectives and constraints
  • Time-series modellingAdvancedModel temporal dependencies and forecasts
  • Data pipelinesWorkingBuild reliable ingestion and transformation systems
  • Probability and statisticsWorkingQuantify variability and statistical evidence

Other roles in supply chain, logistics and mobility analytics

Hiring nowLogistics Optimisation EngineerA Logistics Optimisation Engineer turns routing, scheduling and allocation problems into models that produce workable plans. They cut cost and…Hiring nowWarehouse AI Systems SpecialistA Warehouse AI Systems Specialist connects models and automation to the way a warehouse actually runs. They raise throughput and accuracy without…Hiring nowMobility Demand ScientistA Mobility Demand Scientist forecasts how and where people and goods will travel, then tests how transport capacity is allocated. They help a…

Related roles in other families

Hiring nowForecasting Data ScientistForecasting, optimisation and recommendationA Forecasting Data Scientist produces calibrated demand and operational forecasts that planning, inventory and staffing decisions can rely on…Hiring nowOperations Research AnalystForecasting, optimisation and recommendationAn Operations Research Analyst turns messy business decisions into optimisation models with explicit constraints. They help a company allocate…Hiring nowRecommendation Systems EngineerForecasting, optimisation and recommendationA Recommendation Systems Engineer builds the ranking systems that decide what each user sees, and keeps them honest with feedback controls. Good…Hiring nowRanking and Search ScientistForecasting, optimisation and recommendationA Ranking and Search Scientist improves the order in which items appear for a defined information need. Better ordering means users find what they…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← Supply chain, logistics and mobility analyticsAll new job families

Start a search

Hiring a Supply Chain AI Scientist?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.