Astrocade is an AI technology company building super-intelligence for the interactive world, delivered through a breakout consumer platform.

Today's frontier models can write, reason, and generate video. None can build a world you can step into and act on. Interactive world models are one of the defining problems on the path to ASI, and the foundation of the next great consumer platform. Interactivity is the holy grail of content: not something you watch, but something that responds to you. We're further ahead than anyone: the only team building the intelligence and the platform together, and both are already live.

Our social UGC platform lets anyone create and play interactive experiences through natural language. And it's one of the fastest-growing consumer products in the world, with over 30 million users in just months since launch. Creators bring to life games, companions that remember and grow with them, learning experiences that adapt like a great tutor, and social worlds built with friends. The platform also powers our research with data no video dataset contains: millions of creators prompting and refining gives us paired data of human intent and the worlds that fulfill it, and every play session produces ground-truth, action-labeled interaction data at scale. All of it flows back into our models, and research ships to real players in days, spinning a flywheel no one else can build.

We are a small team from Google Research, Meta, FAIR, Character.ai, and Stanford, led alongside Fei-Fei Li, with frontier-scale compute and direct ownership of core model problems. We are backed by Sequoia Capital, Google, NVIDIA, and luminaries including Eric Schmidt and Jerry Yang.

The next foundational AI company will be built where world models meet a billion players. We're the rare place where frontier research and a breakout consumer platform are one company, and where your work ships to millions, not to a paper. Come build it with us.

About the Role

Our recommendation system doesn't exist yet, and it needs to. We have a large and fast-growing catalog of games, millions of users, and new content being created every day. What you show someone, and when, is the difference between a session that lasts two minutes and one that lasts two hours. As our RecSys founding member, you'll own this problem end-to-end - set the architecture, build the foundation, and grow it from rule-based systems to deep learning. The decisions made now will shape how discovery works on the platform for years.

You'll report to the CTO, and work directly with the co-founders. This is a 0 to 1 build with full ownership.

What You'll Do

Design and build the systems that decide which games surface to which players, from candidate retrieval through final ranking

Own the full data pipeline - ingestion, feature engineering, training data construction, and low-latency serving

Build personalization systems and models that adapt to user behavior, preferences, and context over time

Build eval infrastructure to measure recommendation quality: offline metrics, online experiments, and business outcomes

Run A/B tests and translate results into concrete system improvements

Instrument the recommendation stack deeply so the team can move fast with confidence

You'd Be a Great Fit If You

Have 4-7+ years of experience in recommendation systems, ML engineering, or applied ML in a consumer context

Have built ranking or personalization systems end-to-end - feeds, video, gaming, or similar

Experience running recommendation evals end-to-end (offline + online)

Understand the full stack - data pipelines, feature stores, model training, and serving

Are comfortable making architectural decisions on a greenfield system without much scaffolding

Are self-directed and energized by ownership, not just execution

Bonus Points

Experience at companies with large-scale consumer recommendation systems (YouTube, Netflix, TikTok, Instagram, LinkedIn, Twitter/X)

Familiarity with both rule-based and deep learning approaches, and when to use each