Hiring nowForecasting, optimisation and recommendation

Recommendation Systems Engineer

Also called Recommender Engineer

A Recommendation Systems Engineer builds the ranking systems that decide what each user sees, and keeps them honest with feedback controls. Good ones lift user value without narrowing exposure or treating groups unfairly.

What they do

Builds and runs the pipeline that picks candidates for each user and then ranks them. Starts with a simple baseline, then improves it with better features, learning from feedback and sensible constraints. Sets up offline tests and live experiments so changes are judged on evidence. Watches for feedback loops, where the system only shows what it already shows. Adds controls for diversity, fairness and exposure. Works with product, data and platform teams to ship a service that is fast, observable and easy to change.

What a strong hire delivers

Within the first months, a working recommendation service with a clear baseline and a record of what beats it. An offline evaluation set that predicts live results reasonably well. A live experiment setup the team trusts. Written guardrails for diversity, fairness and exposure, with monitoring that flags drift. A short list of next improvements ranked by expected user value and effort.

How you can tell they are good

Ask them to walk through a ranking system they shipped, from candidate generation to the final order. Listen for how they chose metrics, and what happened when offline and online results disagreed. Ask how they spotted a feedback loop and what they changed. Strong people talk about trade-offs and failures plainly. Be wary of those who only name models.

Why it is hard to fill

Titles are inconsistent. The same work appears as recommender engineer, ranking engineer, applied scientist or data scientist. Many candidates have built models but never owned a live service with guardrails. Others come from operations research and know constraints well but have little feedback-driven experience. The overlap of ranking, experimentation and production ownership is small, so good people are usually already employed and selective.

Where to find them

Look in consumer products with feeds, search, marketplaces, media and commerce, where ranking is a core system. Titles include recommender engineer, ranking engineer, search relevance engineer, applied scientist and machine learning engineer. Strong adjacent candidates come from data science, operations research and applied mathematics, especially those who have run experiments and moved work into production.

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 Recommendation Systems Engineer

  1. Describe a recommendation system you shipped. What were the candidate generation and ranking stages, and what did you own?

    A strong answer separates retrieval from ranking and states clear ownership. They explain why each stage exists, what they measured and what they changed after launch. Worry if they describe only a model or take credit for the whole team's work.

  2. Offline metrics improved but the live experiment showed nothing. What do you do next?

    Good answers check for logging bugs, biased training data, metric mismatch and novelty effects before blaming the test. They propose a way to make offline evaluation more predictive. Worry about those who trust offline numbers regardless of live results.

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

Job description you can post

We are looking for a Recommendation Systems Engineer to build and run the personalised ranking that decides what our users see. You will own the service from candidate generation to evaluation, and set the controls that keep results useful, diverse and fair.

What you will do

  • Build and maintain candidate generation and ranking services
  • Design offline evaluation and live experiments for ranking changes
  • Use feedback signals to improve results while avoiding feedback loops
  • Implement guardrails for diversity, fairness and exposure
  • Monitor quality, drift and latency in production
  • Work with product and data teams to prioritise improvements
  • Document decisions, metrics and known limits

What you will bring

  • Shipped a ranking or recommendation system used by real users
  • Sound grounding in probability, statistics and experimental design
  • Examples of offline results compared against live outcomes
  • Practical experience with candidate generation and ranking methods
  • Comfortable writing production code and working with data pipelines
  • Clear communication of trade-offs to non-specialists

Nice to have

  • Experience with optimisation or operations research methods
  • Time-series modelling experience
  • Work on fairness or exposure measurement in marketplaces

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

Skills that matter

  • Time-series modellingAdvancedModel temporal dependencies and forecasts
  • Optimisation and operations researchAdvancedChoose actions subject to objectives and constraints
  • Probability and statisticsWorkingQuantify variability and statistical evidence
  • Experimental designWorkingChoose comparisons that identify credible effects

Other roles in forecasting, optimisation and recommendation

Hiring nowForecasting Data ScientistA Forecasting Data Scientist produces calibrated demand and operational forecasts that planning, inventory and staffing decisions can rely on…Hiring nowOperations Research AnalystAn Operations Research Analyst turns messy business decisions into optimisation models with explicit constraints. They help a company allocate…Hiring nowRanking and Search ScientistA Ranking and Search Scientist improves the order in which items appear for a defined information need. Better ordering means users find what they…

Related roles in other families

Hiring nowQuantitative ML ResearcherInvestment, quantitative finance and market AIA Quantitative ML Researcher tests investment ideas with models and builds evidence that holds up after costs and constraints. They stop the company…Hiring nowAI Portfolio Analytics ScientistInvestment, quantitative finance and market AIAn AI Portfolio Analytics Scientist models portfolio risk and the tradeoffs behind investment decisions. They give the company reliable risk…Hiring nowAI Execution ResearcherInvestment, quantitative finance and market AIAn AI Execution Researcher builds and tests models that decide how to trade orders under market and cost constraints. Done well, it lowers the cost…EmergingInvestment Research AI Workflow SpecialistInvestment, quantitative finance and market AIThis person builds AI assistance for investment research where every claim links back to its source and an analyst can check it. It matters because…

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.

← Forecasting, optimisation and recommendationAll new job families

Start a search

Hiring a Recommendation Systems Engineer?

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.