Intelligent Customer Preference engine with real-time ML systems

apply(conf) - May '22 - 30 minutes

In an omni-commerce space such as Walmart, Personalization is the key to enable customer journeys tailored to their individual needs, preferences and routines. Moreover, in e-commerce, customers’ needs and intent evolve with time as they navigate and engage with hundreds of millions of products. Real-time session-aware ML systems are best suited to adapt to such changing dynamics and can power intelligent systems to provide 1:1 personalized customer experiences, from finding the product to delivering it to the customer. In this talk we will look at how we leverage session features to power customer preference engines in real-time applications at Walmart scale.

Manoj Agarwal

Architect Fellow

Walmart Global Tech

Manoj has 25 years of strong distributed systems and ML Platforms experience. Currently, he is an Architect Fellow at Walmart, making e-Commerce smarter with AI. Previously, At Salesforce, he architected a brand-new comprehensive machine learning platform designed to serve millions of models and billions of inferences per day. He has been building Search and ML platforms for the last ten years. He modernized the search middleware at Yahoo and was an initial architect of the Amazon Visual Search platform. He holds 10+ patents in the Search and ML area.

Earlier in his career, he enjoyed building cloud platforms. He was a founding member of the Azure team at Microsoft; he led a team delivering a b2b integration suite of services to Azure. His cloud platforms passion led him to work at Rackspace, contributing to the OpenStack control plane.

Manoj likes to share his knowledge at various meetups and conferences; recently, he presented at the IEEE Infrastructure Conference, AI DevWorld,, and other meetup groups.

He likes to play board games and explore bay area hikes with his wife and two young adult children in his spare time.

Praveen Kumar Kanumala

Principal Software Engineer

Walmart Global Tech

Praveen is a Principal Software Engineer of Personalization & Recommendations at Walmart Global Tech with 10+ years of experience working on distributed systems, Micro-Services and ML Inference Platforms. In his current role, he is leading a group of engineers building multi-model framework ML inference platforms, Similarity Vector Data Store and Interleaving Testing platform for ranking algorithms. which can server millions of requests and also power the core models of Personalization. During his previous roles at Walmart, he was instrumental in building catalog services for He likes to drive innovation, research in the space of ML platforms focused on Real time Inference in Recommender and Personalization area. During his free time, he likes to watch movies and spend time with his family.