Machine Learning Engineer - Relevance & Learning Systems

Job description

About Wizard Wizard is the top-performing AI Shopping Agent, delivering the best products from across the web with unmatched accuracy, quality, and trust. The Role: We’re looking for a Machine Learning Engineer to design and build feedback driven learning systems that improve our AI agent over time. This is not a traditional RL research role, we’re focused on building systems that learn from real user behavior and improve production. You’ll be working at the intersection of a live conversational agent and real shopping behavior – the feedback signal quality here is unusually rich compared to traditional search. You’ll focus on turning user interactions into learning signals, designing practical feedback loops and shipping systems that continuously improve real world outcomes. What You’ll Do: - Build and productionize feedback loops that improve agent performance over time - Build the evaluation infrastructure – offline metrics, regression suites, and experiment analysis - Own the signal pipelines end-to-end: instrument events, build clean labeled datasets, and translate user behaviors into reliable learning signals - Design lightweight reinforcement learning / bandit-style approach...