Machine LearningSenior Software Engineer, Machine Learning (Commerce)San Francisco Bay Area

Log In SENIOR SOFTWARE ENGINEER, MACHINE LEARNING (COMMERCE) San Francisco Bay Area See All Jobs Discord is used by over 200 million people every month for many different reasons, but there’s one thing that nearly everyone does on our platform: play video games. Over 90% of our users play games, spending a combined 1.5 billion hours playing thousands of unique titles on Discord each month. Discord plays a uniquely important role in the future of gaming. We are focused on making it easier and more fun for people to talk and hang out before, during, and after playing games. We are looking for a Senior Machine Learning Engineer to join our Revenue ML team at Discord. This role sits at the intersection of Discord's two most strategic revenue pillars — our growing 1P Shop and our newly launched Game Commerce platform, which connects players to in-game items from major publishers like Marvel Rivals, Fortnite, Valorant, and more. You'll be the founding ML voice for commerce discovery and personalization, building systems from the ground up that power recommendations, social commerce mechanics, and marketing targeting across both first-party and third-party storefronts. This is a high-impact, high-leverage role. Discord's social platform gives us a fundamentally differentiated commerce advantage — deep social graphs, fan communities, and native gaming context — and you will be the person who turns that into ML-powered products that drive meaningful GMV growth. What You'll Be Doing: Architect and own the ML foundations for commerce discovery: user, item, and interaction embeddings that power personalized recommendations across shop surfaces (homepage, cart, post-purchase, wishlist, and more). Design and deploy scalable real-time recommendation and ranking systems that support a growing catalog of 1P and 3P items across heterogeneous game publisher inventories. Build ML-powered marketing targeting systems that identify the right users for the right campaigns — new buyer discounts, drop campaigns, weekly deals, and seasonal promotions — driving conversion without conditioning users to wait for discounts. Leverage Discord's unique social graph to build social commerce ML: gifting recipient prediction, group buying conversion modeling, and friend-group recommendations that differentiate Discord from traditional game storefronts. Drive deep learning A/B testing infrastructure and model monitoring to translate experimentation results into actionable product decisions. Partner closely with Shop, Game Commerce, Revenue Infra, ML Infra and Data Engineering teams to define ML requirements, surface integration points, and influence the commerce roadmap. What You Should Have: 4+ years of experience as a Machine Learning Engineer, with a track record of owning and shipping recommendation or personalization systems end-to-end. Deep expertise in applied deep learning — particularly embedding models, two-tower architectures, and retrieval/ranking systems for e-commerce or content recommendation. Strong proficiency in Python and deep learning frameworks (PyTorch preferred). Experience building and operating real-time ML serving infrastructure at scale, including feature stores, model serving, and A/B testing frameworks. Demonstrated ability to work in early-stage, high-ambiguity environments and build ML systems from the ground up, not just improve existing ones. Experience translating ML evaluation metrics and experiment results into product roadmap decisions and business impact. Strong cross-functional instincts — you're comfortable partnering with product, engineering, data science, and business stakeholders to align on priorities and drive execution. Bonus Skills: Experience applying graph ML or social network signals (social affinities, community behavior) to recommendation or personalization problems. Familiarity with personalized marketing systems: lifecycle targeting, audience segmentation, and campaign optimization. Familiarity with l ... (truncated, view full listing at source)