Principal Applied Scientist - Recommendation & Personalization

About Us

Wizard is revolutionizing the shopping experience using the power of generative AI and rich messaging technologies to build a personalized shopping assistant for every consumer. We scour the entire internet of products and ratings across brands and retailers to find the best products for every consumer’s personalized needs. Using an effortless text-based interface, Wizard AI is always just a text away. The future of shopping is here. Shop smarter with Wizard.

The Role

Wizard is seeking a Principal Applied Scientist to spearhead our recommendation and personalization systems. This role will drive the research, development and implementation of our recommendation algorithms. The role extends beyond traditional boundaries, requiring the candidate to innovate in model optimization, system scalability, and the integration of cutting-edge AI technologies to redefine conversational experiences. As a principal scientist & engineer, you will set the technical direction and mentor a team of ML engineers, influence our AI strategy, and collaborate with cross-functional teams to drive product innovation and excellence.

Key Responsibilities:

• Architect and oversee the development of a Wizard’s recommender system
• Develop a product ranking model that takes into account both customer profiles and dialog context
• Find the right balance between exploration and optimization to curate recommendations that improve conversion rates in the long run.
• Working with Product and Engineering counterparts, translate customer needs and business requirements into long term vision and roadmap for recommendation and personalization at Wizard
• Act as a thought leader within the company, staying abreast of the latest advancements in the Generative AI field and integrating innovative technologies into our systems to maintain a competitive edge.

You

• Ph.D.in Computer Science, Mathematics, or another quantitative field or outstanding professional experience in machine learning engineering.
• Over 5 years of industry experience in machine learning, with a proven track record of developing ML-driven products at scale.
• Experience building recommender systems, preferably in the e-commerce space.
• Demonstrated expertise in tackling complex problems using machine learning frameworks like PyTorch.
• A comprehensive understanding of ML system design in production environments, including a quantitative approach to evaluating performance bottlenecks and cost/performance trade-offs.
• Hands-on experience with large-scale data systems, sophisticated data models, and batch and streaming data pipelines.
• Quick adaptability to our technology stack encompasses GCP, Kubernetes, Airflow, Pandas, PyTorch, Python, and Node.js.
• Deep experience in model deployment strategies, …