Senior Data Scientist (Traveltech)

About the Company

At deRecruiters, we’re searching for a Senior Data Scientist for a travel tech scaleup that is a pioneer in airline inventory and post-booking revenue management technology. The company helps airlines move from static to dynamic post-booking inventory, so they can increase conversion, improve revenue optimization and give passengers more flexibility. Its platform connects existing airline systems with new inventory logic. This enables upselling, seat upgrades and flight swaps without disrupting core infrastructure. The company works with leading low-cost and regional carriers across LATAM and Asia.

Mission

The Senior Data Scientist will own ML models end to end, trained for each airline the company serves. As a model specialist, they will make their models better, prove their value to the business, and make them work for each new airline and each future company solution.

Primary Focus

The role holds specialist ownership of one or more model families across all tenants: research, feature engineering, experiments, releases and business impact. It reports to the Lead Data Scientist and works closely with MLOps, Data Engineering, Product and Performance.

Key Responsibilities

Model Ownership

• Own one or more model families across all airline tenants, for example full-flight and spill prediction, expected resale value, price elasticity (willingness to accept), swap quality, or seat-value models.

• Define and deliver their roadmap of upgrades, in line with the Lead Data Scientist’s model ecosystem.

• Build each model on a single shared feature store, trained separately for each airline on its own isolated data.

Modeling & Features

• Develop features from booking position and momentum, pacing, fare-class dynamics, calendar, network and market signals.

• Build well-calibrated probabilistic models, and tune them for the business trade-off that matters, such as recall on full flights at a fixed precision.

• Extend models toward O&D and multi-carrier settings as the company’s solutions evolve.

Experiments & Releases

• Run experiments and release new versions as challengers through the ML pipeline: offline evaluation, a promotion gate against the champion, shadow, then promotion.

• Make sure no segment gets worse when a new version ships, and own monitoring and retraining decisions with MLOps.

Business Impact

• Quantify how the models’ predictive performance translates into business performance at each step of the operational funnel, per airline.

• Explain results to Product and Performance in business terms, and recommend product changes based on what the model reveals.

Airline Deployments

• Onboard new airlines onto their models: assess their data and RM context, warm the models with history, and validate them before go-live.

• Support airline-facing technical discussions about the models and their methodology.

Agentic Data Science

• Work with the DS Expert agent to automate routine experiments and feature exploration, and help shape what it does.

• Document the models, their features and methodology as governed skills in the company’s knowledge layer, so people and agents use the same context.

Core Tools

• Python (scikit-learn, XGBoost/LightGBM, PyTorch) and SQL (BigQuery)

• Google Cloud: Vertex AI Pipelines and Model Registry, BigQuery

• Claude Code and agentic workflows (skills, MCP)

• Jira for prioritization and change management

Ideal Candidate

• 5+ years of applied data science, with models they built, shipped and improved in production.

• Strong in probabilistic classification, forecasting, calibration, and elasticity or choice modeling.

• Rigorous experimenter: champion/challenger, offline vs. online evaluation, segment analysis and statistically sound comparisons.

• Strong Python and SQL; writes reproducible, reviewable code.

• Business-minded: measures success in airline revenue, not only in model metrics.

• AI-native: uses AI assistants and coding agents daily to multiply productivity and shorten time to market.

• Clear communicator in English with technical and business audiences.

Nice to Have

• Airline revenue management, pricing or demand forecasting experience; familiarity with RM systems such as PROS, Amadeus, Sabre or Navitaire.

• Causal inference or counterfactual measurement of model impact.

• Experience building or working with agents that automate data science work.