Senior Machine Learning Engineer

Role Overview As a Senior Machine Learning Engineer, you will design, build, and scale production-grade algorithmic solutions that directly impact our digital commerce platform. Operating at the intersection of deep learning, reinforcement learning, and distributed computing, you will tackle complex real-world challenges—ranging from real-time dynamic pricing and personalization to generative AI travel assistants and demand forecasting. You will collaborate closely with cross-functional product and engineering teams to deploy low-latency, high-throughput models that serve millions of users and drive measurable business impact. Key Responsibilities Dynamic Pricing & Revenue Management: Design and implement reinforcement learning (RL) and contextual bandit algorithms to optimize real-time pricing, personalized discounts, and multi-product bundling strategies. Search, Ranking & Personalization: Develop advanced deep learning architectures (e.g., Two-Tower models, Graph Neural Networks, and Transformers) to rank offerings, inventory, and experiences based on real-time user intent, historical behavior, and high-dimensional contextual signals. Generative AI & Conversational Commerce: Build and fine-tune Large Language Models (LLMs) to power next-generation AI assistants, automating complex itinerary planning and multi-modal customer support. Supply-Demand Forecasting: Construct high-precision spatio-temporal forecasting algorithms to predict demand surges, booking cancellation probabilities, and market competitiveness. Low-Latency Inference: Optimize complex deep learning models to execute within milliseconds, ensuring real-time search results are served seamlessly during peak traffic periods. Distributed Infrastructure: Architect and scale distributed training pipelines using frameworks like PyTorch, Ray, or DeepSpeed over massive datasets consisting of billions of real-time clickstream events and transactional records. Algorithmic Guardrails: Implement rigorous evaluation frameworks, multi-variant A/B testing systems, and counterfactual reasoning methods to measure the true causal impact of algorithmic changes on conversion rates and Gross Bookings Value (GBV). Required Qualifications 8+ years of professional experience building, deploying, and scaling advanced machine learning algorithms in a high-throughput, customer-facing digital economy. Master’s or Ph.D. in Computer Science, Operations Research, Applied Mathematics, Data Science, or a highly quantitative field. Programming Mastery: Expert proficiency in Python or SQL with a focus on writing production-grade, highly optimized code. ML/AI Ecosystem: Deep expertise in PyTorch , TensorFlow/JAX , and classical ML stacks (Scikit-Learn, XGBoost, LightGBM). Domain Specifics: Proven track record in at least two of the following mathematical/algorithmic domains: Learning-to-Rank (LTR) frameworks and collaborative filtering. Multi-armed bandits and Reinforcement Learning (QQQ-learning, policy gradients) applied to pricing or allocation. Time-series forecasting at scale (DeepAR, Prophet, or custom neural forecasting architectures). Large-scale anomaly detection/classification for payment and account fraud. Big Data & Cloud Infrastructure: Strong hands-on experience working with Spark, Kafka/Flink, Airflow, and cloud ecosystems (AWS, GCP, or Azure).