CloudIngest
Senior Data Scientist (AIOps & MLOps) – W2 only
CloudIngest, Granite Heights, Wisconsin, United States
bSenior Data Scientist — Forecasting, AI-Ops & ML-Opsb
bContract Opportunity | Irving, TXb
Position Overview and Key Responsibilities We’re seeking a senior Data Scientist with deep expertise in bforecastingb and bmarket expansionb for the bhospitality (hotels)b sector. You’ll build and productionize models that identify and size demand in bnew geographic marketsb , accelerate bb2b/new-logo acquisitionbb , and guide pricing, sales targeting, and inventory strategy. You’ll own the end-to-end lifecycle—from data discovery and modeling to bAIOps/MLOpsb and clear, executive-level storytelling.
What you’ll do
Forecasting for expansion:
Design hierarchical and geospatial time-series models to predict room-night demand, RevPAR/ADR, lead volume, and conversion potential across new markets and sub-markets.
New business acquisition modeling:
Build propensity and LTV models for corporate accounts, tours, and groups; prioritize high-value segments and whitespace geographies.
Causal & scenario analysis:
Run MMM/causal inference to quantify marketing/sales lift; simulate “what-ifs” for pricing, distribution, channel mix, and opening timelines.
Decision storytelling:
Translate findings into crisp narratives and visuals for executives, development, sales, and revenue management—turn models into action.
MLOps ownership:
Productionize pipelines (data → features → model → service), implement CI/CD, versioning, model registry, and automated testing.
AIOps & reliability:
Set up monitoring, drift detection, alerting, SLA/SLOs, and incident playbooks to keep models healthy post-launch.
Deployment strategy:
Choose and execute batch/real-time/streaming deployments; run shadow, canary, blue-green releases; measure impact and rollback as needed.
Partner cross-functionally:
Work with RevOps, Sales, Marketing, Development, and Finance to align models with business targets and P&L.
Tech stack you’ll use
Python & data:
pandas, NumPy, scikit-learn, statsmodels, Prophet/darts, XGBoost/LightGBM; optional: PyTorch/TensorFlow.
Geospatial/time series:
GeoPandas, shapely, H3, raster/tiling basics; hierarchical & intermittent demand methods.
Visualization & storytelling:
bTableaub (must-have), plus notebooks and executive dashboards.
MLOps/AIOps:
MLflow/Weights & Biases, feature stores, model registry; Evidently/Arize/Fiddler for monitoring; Docker, Kubernetes; Airflow/Prefect; GitHub Actions/GitLab CI.
Data & cloud:
SQL, dbt; Snowflake/BigQuery/Redshift; AWS/GCP/Azure services.
Key Qualifications and Skillset for this Role Must-haves
5–8 years in applied data science with a focus on bforecasting/time-seriesb and bmarket expansionb ; bhospitality/hotelsb experience strongly preferred.
Track record deploying models to production with bMLOpsb best practices and bAIOpsb observability.
Exceptional bstorytellingb skills—turn complex analyses into simple, persuasive narratives for senior leadership.
Advanced SQL and Python; expert with bTableaub dashboards for executives and operators.
Experience with geospatial datasets (supply, demand, comp sets, OTA/search data, mobility, macro indicators).
Nice-to-haves
Causal inference (DiD, uplift, synthetic controls) and MMM.
Knowledge of revenue management, distribution channels, and hotel development cycles.
Experience with privacy-safe data partnerships and clean rooms.
Success metrics
Forecast accuracy (e.g., bMAPE/WAPE/RMSEb) at market and sub-market levels.
Pipeline impact: qualified leads, win rate, and revenue lift in target geos.
Time-to-production, model uptime, latency, and alert MTTR.
Executive adoption: dashboard engagement and decision outcomes tied to model insights.
#J-18808-Ljbffr
Position Overview and Key Responsibilities We’re seeking a senior Data Scientist with deep expertise in bforecastingb and bmarket expansionb for the bhospitality (hotels)b sector. You’ll build and productionize models that identify and size demand in bnew geographic marketsb , accelerate bb2b/new-logo acquisitionbb , and guide pricing, sales targeting, and inventory strategy. You’ll own the end-to-end lifecycle—from data discovery and modeling to bAIOps/MLOpsb and clear, executive-level storytelling.
What you’ll do
Forecasting for expansion:
Design hierarchical and geospatial time-series models to predict room-night demand, RevPAR/ADR, lead volume, and conversion potential across new markets and sub-markets.
New business acquisition modeling:
Build propensity and LTV models for corporate accounts, tours, and groups; prioritize high-value segments and whitespace geographies.
Causal & scenario analysis:
Run MMM/causal inference to quantify marketing/sales lift; simulate “what-ifs” for pricing, distribution, channel mix, and opening timelines.
Decision storytelling:
Translate findings into crisp narratives and visuals for executives, development, sales, and revenue management—turn models into action.
MLOps ownership:
Productionize pipelines (data → features → model → service), implement CI/CD, versioning, model registry, and automated testing.
AIOps & reliability:
Set up monitoring, drift detection, alerting, SLA/SLOs, and incident playbooks to keep models healthy post-launch.
Deployment strategy:
Choose and execute batch/real-time/streaming deployments; run shadow, canary, blue-green releases; measure impact and rollback as needed.
Partner cross-functionally:
Work with RevOps, Sales, Marketing, Development, and Finance to align models with business targets and P&L.
Tech stack you’ll use
Python & data:
pandas, NumPy, scikit-learn, statsmodels, Prophet/darts, XGBoost/LightGBM; optional: PyTorch/TensorFlow.
Geospatial/time series:
GeoPandas, shapely, H3, raster/tiling basics; hierarchical & intermittent demand methods.
Visualization & storytelling:
bTableaub (must-have), plus notebooks and executive dashboards.
MLOps/AIOps:
MLflow/Weights & Biases, feature stores, model registry; Evidently/Arize/Fiddler for monitoring; Docker, Kubernetes; Airflow/Prefect; GitHub Actions/GitLab CI.
Data & cloud:
SQL, dbt; Snowflake/BigQuery/Redshift; AWS/GCP/Azure services.
Key Qualifications and Skillset for this Role Must-haves
5–8 years in applied data science with a focus on bforecasting/time-seriesb and bmarket expansionb ; bhospitality/hotelsb experience strongly preferred.
Track record deploying models to production with bMLOpsb best practices and bAIOpsb observability.
Exceptional bstorytellingb skills—turn complex analyses into simple, persuasive narratives for senior leadership.
Advanced SQL and Python; expert with bTableaub dashboards for executives and operators.
Experience with geospatial datasets (supply, demand, comp sets, OTA/search data, mobility, macro indicators).
Nice-to-haves
Causal inference (DiD, uplift, synthetic controls) and MMM.
Knowledge of revenue management, distribution channels, and hotel development cycles.
Experience with privacy-safe data partnerships and clean rooms.
Success metrics
Forecast accuracy (e.g., bMAPE/WAPE/RMSEb) at market and sub-market levels.
Pipeline impact: qualified leads, win rate, and revenue lift in target geos.
Time-to-production, model uptime, latency, and alert MTTR.
Executive adoption: dashboard engagement and decision outcomes tied to model insights.
#J-18808-Ljbffr