Principal AIgorithm Engineer Search and Recommendation

Who We Are

At OKX, we believe that the future will be reshaped by crypto, and ultimately contribute to every individual's freedom. OKX is a leading crypto exchange, and the developer of OKX Wallet, giving millions access to crypto trading and decentralized crypto applications (dApps). OKX is also a trusted brand by hundreds of large institutions seeking access to crypto markets. We are safe and reliable, backed by our Proof of Reserves.

Across our multiple offices globally, we are united by our core principles:
We Before Me, Do the Right Thing, and Get Things Done. These shared values drive our culture, shape our processes, and foster a friendly, rewarding, and diverse environment for every OK-er. OKX is part of OKG, a group that brings the value of Blockchain to users around the world, through our leading products OKX, OKX Wallet, OKLink and more.

We are looking for a Principal Algorithm Engineer to own the technical direction of OKX's next‑generation social feed recommendation system — evolving it from a content feed into a unified engine that surfaces both content and platform features across tens of millions of users. This is a hands‑on, high‑ownership role at the frontier of recommendation science. You will define the 12–24 month technical roadmap and personally drive its execution — from Transformer‑based ranking today to generative recommendation and LLM‑integrated agent paradigms tomorrow.

Your work directly shapes user retention and platform trading conversion at global scale.

• Drive continuous ranking model iteration with measurable, attributable impact on user retention and trading conversion.
• Build a cross‑domain intent framework spanning content consumption, feature usage, and search — shifting the system from tracking what users clicked to understanding what users are trying to do.
• Chart and execute the technical evolution from Transformer‑based sequential ranking toward generative recommendation, including sequence generation and preference alignment.
• Integrate recommendation and search capabilities into an LLM Agent framework, moving from passive content delivery to proactive intent fulfillment.
• Mentor senior engineers and help define the broader recommendation research and engineering strategy.

• Master's or above in Computer Science, Mathematics, or a related field from a top university; 8+ years of industry experience with 5+ years in core recommendation or search roles.
• Proven end‑to‑end ownership of production recommendation pipelines at 10M+ DAU scale.
• User Intent & Profiling (Core) — Hands‑on experience designing unified intent representations across heterogeneous domains (content / feature / search); demonstrated ability to fuse real‑time behavioral signals with long‑term stable preferences; experience building tiered user profile systems across the full cold‑start → interest exploration → stable preference lifecycle.
• Transformer & Sequential Ranking (Core) — Deep, practitioner‑level command of Attention mechanisms in sequential behavior modeling and their production limitations (DIN / SIM / HSTU evolution); ability to propose independent architectural solutions under real engineering constraints; proficiency in Listwise loss functions (ListMLE / Softmax Loss) and joint multi‑candidate ranking.
• Multi‑Task Training (Core) — Expert‑level knowledge of MMoE / PLE / ESMM architectures; hands‑on experience identifying and resolving gradient conflicts; ability to design composite loss function frameworks from scratch; proven methodology for closing the gap between offline metrics (AUC / NDCG) and live business KPIs.
• Business Attribution (Core) — Hands‑on Uplift Modeling experience; proficiency in Position / Selection Bias correction and prediction probability calibration.

• Familiarity with Semantic Tokenization (FSQ / RQ‑VAE), conditional sequence generation, or RLHF / DPO applied to recommendation systems.
• Engineering experience with LLM Agent frameworks (Tool Use / ReAct) and designing the collaboration boundary between agent‑based and traditional recommendation.
• Hands‑on experience with large‑scale distributed…