Senior Data Scientist Forecasting Revenue Optimization

## About RevOpt RevOpt is an AI-native Revenue Management System (RMS) built specifically for the hospitality industry. We're rebuilding how hotels think about revenue — going beyond rooms to optimize every revenue center: Rooms, Food & Beverage, Spa, and Meetings & Events, in real time. We're a small, focused founding team building something that genuinely hasn't been done well before. If you want to work on hard ML problems that directly drive business outcomes — not just build demo models — this is the role. ## The Role We're looking for a Senior Data Scientist who will own the intelligence layer of RevOpt — the forecasting, optimization, and decision engines that sit at the heart of our product. This is not a support or analytics role. You will be the person who builds, iterates, and owns the ML models that our product runs on. ## What You'll Work On - Demand Forecasting — Build time-series models that predict occupancy, F&B covers, spa bookings, and event demand at day/segment/channel level - Price Optimization — Develop pricing algorithms that recommend optimal rates across room types and ancillary revenue centers in real time - Feature Engineering — Work with hotel PMS data, OTA feeds, weather, events, and economic signals to build high-signal feature pipelines - Model Deployment — Take models from experimentation to production; own the full lifecycle - Decision Policy — Translate model outputs into actionable recommendations for hotel revenue managers ## What We're Looking For ### Must-have: - 6–8 years of hands-on experience in Data Science or ML Engineering (not analytics, not BI) - Strong Python — you write production-quality code, not just notebooks - Solid time-series forecasting experience — ARIMA, Prophet, LSTM, or similar; you've done this in a real business context - Experience owning an ML model end-to-end: data to feature engineering to training to evaluation to deployment - Comfort with SQL and working with messy, real-world structured data ### Strong plus: - Experience in pricing, revenue optimization, demand planning, or supply chain optimization - Background in hospitality tech, OTA/travel, or marketplace pricing - Familiarity with MLOps — model versioning, monitoring, retraining pipelines - Any work with multi-variate forecasting or reinforcement learning for decision-making ## What This Is Not - This is not a research role — we care about models that work in production, not papers - This is not a data analyst role — if your primary output is dashboards and SQL reports, this isn't the right fit - This is not for someone who needs a fully defined problem — you'll be shaping what we build ## Why Join RevOpt - Greenfield ML problem — Revenue management for hotels is almost entirely manual and broken. You won't be maintaining legacy models or fitting into someone else's architecture. You'll design, build, and own the forecasting and optimization layer from the ground up. - Fast feedback loop — In most DS roles, your model goes into a pipeline and you never see the business outcome. Here, your forecasting output directly drives pricing decisions and revenue for real hotels. You'll see the impact of your work quickly and clearly. - Become the domain expert — Hospitality revenue intelligence is an extremely specialized and globally underserved space. Spending 2–3 years building this gives you a depth of expertise — in multi-revenue-center optimization, dynamic pricing, demand forecasting — that very few data scientists in India have. That compounds into your career permanently. - Founding team access — You'll work directly with the founders, not filtered through three layers of management. Your technical decisions will shape the product architecture and roadmap. If you've been a cog in a large company, this is the opposite of that. - Chennai-based, stable environment — We're building for the long term, not a sprint. This is a role where you can go deep, not just move fast. **Describe one ML model or forecasting system you built end-to-end — what was the business problem, what approach did you take, what was the outcome, and what would you do differently today?**