Principal Algorithm Engineer, Search and Recommendation

Responsibilities

• Drive continuous ranking model iteration to improve user retention and trading conversion
• Build a cross-domain intent framework spanning content consumption, feature usage, and search
• Lead the technical evolution from Transformer-based sequential ranking toward generative recommendation and LLM-integrated agent paradigms
• Integrate recommendation and search capabilities into an LLM Agent framework for proactive intent fulfillment
• Mentor senior engineers and define the broader recommendation research and engineering strategy

Requirements

• Master's or above in Computer Science, Mathematics, or a related field
• 8+ years of industry experience, with at least 5 years in core recommendation or search roles
• Proven ownership of production recommendation pipelines at a scale of 10M+ DAU
• Deep expertise in Transformer-based sequential ranking and Attention mechanisms
• Expert-level knowledge of multi-task training architectures such as MMoE, PLE, or ESMM
• Hands-on experience with Uplift Modeling and business attribution

Preferred Qualifications

• Familiarity with Semantic Tokenization, conditional sequence generation, or RLHF/DPO applied to recommendations
• Engineering experience with LLM Agent frameworks (Tool Use / ReAct)
• Experience with large-scale distributed training (10B+ parameter models) and real-time feature pipelines (Flink/Kafka)
• Background in fintech, Web3, or crypto platforms

Benefits

• Competitive total compensation package
• L&D programs and education subsidies for professional growth
• Various team building programs and company events
• Wellness and meal allowances
• Comprehensive healthcare schemes for employees and dependents

About the Company

OKX is a leading crypto exchange and the developer of OKX Wallet, providing millions of users access to crypto trading and decentralized applications. We are a global team united by our core principles: We Before Me, Do the Right Thing, and Get Things Done.