Data Scientist

Modeling & ML Frameworks : Python, scikit-learn, PyTorch, TensorFlow — spanning classical ML, deep learning, and transformer-based architectures. Includes modern ensemble methods (XGBoost, LightGBM) for large-scale structured modeling.

Applied Domains : Ranking, Recommendation, Dynamic Pricing, Forecasting, Supply–Demand Optimization, Semantic Search, NLP / NLU, Generative Content Systems

Data & Compute : Databricks, PySpark, AWS (S3, Glue, EMR, Athena), ScyllaDB, MongoDB, Redis

Experimentation & Optimization : MLflow, Airflow, SageMaker, Bayesian Optimization, Bandit / Sequential Experimentation

LLMs & GenAI : Claude, OpenAI GPT-4, SLMs, LangChain, Cursor IDE, RAG Pipelines, Embedding Models, Vector Search (FAISS / Pinecone)

Observability : Grafana, Prometheus, Data Quality Monitors, Custom Model Dashboards

We’re in the early stages of building a Data Science & AI team — the learning curve, innovation velocity, and ownership opportunities are immense. You’ll help define the foundation for experimentation, production ML pipelines, and GenAI innovation from the ground up.

We’re hiring a Senior Data Scientist to build the next generation of intelligent decision systems that power pricing, supply optimization, ranking, and personalization in our global B2B hotel marketplace.

This is a high-impact role at the intersection of machine learning, optimization, and product engineering, where you’ll leverage deep statistical modeling and modern ML techniques to make real-time decisions at scale.

You’ll collaborate closely with Product, Engineering, and Data Platform teams to operationalize data science models that directly improve revenue, conversion, and marketplace efficiency.

You’ll own the full lifecycle of ML models—from experimentation and training to deployment, monitoring, and continuous retraining to ensure performance at scale.

Responsibilities :

• Design and implement ML models for dynamic pricing, availability prediction, and real-time hotel demand optimization.
• Develop and maintain data pipelines and feature stores supporting large-scale model training and inference.
• Leverage Bayesian inference, causal modeling, and reinforcement learning (bandits / sequential decision systems) to drive adaptive decision platforms.
• Build ranking / recommendation systems for personalization, relevance, and supply visibility.
• Use LLMs (Claude, GPT-4, SLMs) for :

○ Contract parsing, metadata extraction, and mapping resolution

○ Semantic search and retrieval-augmented generation (RAG)

○ Conversational systems for CRS, rate insights, and partner communication

○ Automated summarization and content enrichment

Requirements

Nice to Have