Senior/Lead Algorithm Engineer, Overseas Growth
OkxSingapore, SingaporePosted 12 March 2026
Job Description
OKX will be prioritising applicants who have a current right to work in Singapore, and do not require OKX's sponsorship of a visa.
Who We Are
At OKX, we believe that the future will be reshaped by Crypto, ultimately contributing to every individual's freedom.
OKX began as a crypto exchange giving millions of people access to crypto trading and over time becoming among the largest platforms in the world. In recent years, we have developed one of the most connected Web3 wallets used by millions to access decentralized crypto applications (dApps).
OKX is a trusted brand by hundreds of large institutions seeking access to crypto markets on a reliable platform that seamlessly connects with global banking and payments. In the last year, OKX has expanded into new markets including Australia, Brazil, Netherlands, Singapore and Turkey, with plans to launch in the US, Belgium and the UAE.
We are deeply committed to shaping a fairer, more transparent and accessible society through blockchain technology. This is why we publish proof of reserves monthly, and continue to ship new innovative security features.
About the Opportunity
We're looking for a Senior/Lead Algorithm Engineer to build our overseas growth algorithm capabilities from the ground up . You'll design and implement end-to-end ML systems that optimize paid advertising (Google, Meta), intelligent user targeting, and LTV prediction across 100+ countries and millions of users.
This is a high-impact role with significant ownership - you'll define the technical direction, build scalable systems, and directly influence how OKX acquires and retains high-value users globally. As the area matures, you'll have the opportunity to scale the team and grow into Staff Engineer or Engineering Manager roles.
What You’ll Be Doing
Paid Ads Optimization
Design intelligent bidding algorithms for Google Ads, Meta Ads, and other paid channels to optimize CPA, ROAS, and user quality
Build automated budget allocation systems across campaigns, geos, and channels based on real-time performance and predicted LTV
Develop creative performance prediction models to guide A/B testing
Implement multi-touch attribution models to accurately measure channel contribution
User Targeting Selection
Build lookalike modeling and audience expansion algorithms to identify high-value user segments
Design propensity models for conversion prediction at different funnel stages (registration, KYC, deposit, first trade)
Develop real-time user scoring systems to optimize bid adjustments and personalized experiences
Create behavioral clustering models to identify user personas and refine targeting strategies
LTV
Prediction Retention
Build LTV prediction models incorporating user behavior, market conditions, and engagement patterns
Develop early signals detection to identify high-LTV users within 24-72 hours
Design churn prediction and reactivation models to optimize retention campaigns
Implement cohort analysis to track performance across channels and time periods
What We Look For In You
3+ years of hands-on experience in growth algorithms, performance marketing, or user acquisition optimization
Strong expertise in ML frameworks: PyTorch, TensorFlow, XGBoost, LightGBM
Proficiency in Python and SQL; experience with big data processing (Spark, Flink, or similar)
Demonstrated ability to work independently and drive 0→1 projects
Proficiency in speaking, reading and writing in both English and Mandarin to collaborate effectively with global and cross-functional team members.
Nice to Haves
Background in fintech, cryptocurrency, or high-growth tech companies (ByteDance, Alibaba, Tencent, Meta, Google, etc.)
Knowledge of blockchain technology and crypto user behavior
Experience with deep learning for sequence modeling and user behavior prediction
Perks Benefits
Competitive total compensation package
LD programs and Education subsidy for employees' growth and development
Various team building pro ... (truncated, view full listing at source)