Senior ML Scientist (Optimization & Reinforcement Learning) – US/Canada

Role Overview

We seek a Senior ML Scientist to drive innovation in AI ML-based dynamic pricing algorithms and personalized offer experiences. This role will focus on designing and implementing advanced machine learning models, including reinforcement learning techniques like Contextual Bandits, Q-learning, SARSA, and more. By leveraging algorithmic expertise in classical ML and statistical methods, you will develop solutions that optimize pricing strategies, improve customer value, and drive measurable business impact.

Key Responsibilities

· Algorithm Development: Conceptualize, design, and implement state-of-the-art ML models for dynamic pricing and personalized recommendations.

· Reinforcement Learning Expertise: Develop and apply RL techniques, including Contextual Bandits, Q-learning, SARSA, and concepts like Thompson Sampling and Bayesian Optimization, to solve pricing and optimization challenges.

· AI Agents for Pricing: Build AI-driven pricing agents that incorporate consumer behaviour, demand elasticity, and competitive insights to optimize revenue and conversion.

· Rapid ML Prototyping: Experience in quickly building, testing, and iterating on ML prototypes to validate ideas and refine algorithms.

· Feature Engineering: Engineer large-scale consumer behavioural feature stores to support ML models, ensuring scalability and performance.

· Cross-Functional Collaboration: Work closely with Marketing, Product, and Sales teams to ensure solutions align with strategic objectives and deliver measurable impact.

· Controlled Experiments: Design, analyze, and troubleshoot A/B and multivariate tests to validate the effectiveness of your models.

Qualifications

· 8+ years in machine learning, 5+ years in reinforcement learning, recommendation systems, pricing algorithms, pattern recognition, or artificial intelligence.

· Expertise in classical ML techniques (e.g., Classification, Clustering, Regression) using algorithms like XGBoost, Random Forest, SVM, and KMeans, with hands-on experience in RL methods such as Contextual Bandits, Q-learning, SARSA, and Bayesian approaches for pricing optimization.

· Proficiency in handling tabular data, including sparsity, cardinality analysis, standardization, and encoding.

· Proficient in Python and SQL (including Window Functions, Group By, Joins, and Partitioning).