Senior Recommendation & Growth ML Engineer

WorkInCryptoGlobal•San Francisco, CA

25d•Onsite

About The Position

We are looking for a Senior Recommendation & Growth ML Engineer to build and scale the machine learning systems that power personalization, user growth, and intelligent product discovery across Bybit’s ecosystem. This role sits at the intersection of recommendation systems, growth engineering, experimentation, and AI-driven personalization. You will own the end-to-end development of large-scale recommendation and growth optimization systems that drive engagement, retention, conversion, and user lifetime value across trading products, campaigns, community experiences, and AI-powered investment services. You will work closely with Product, Data Science, TradeGPT, Community, and Engineering teams to translate business objectives into scalable machine learning systems serving millions of users globally. This is a highly impactful role for someone who combines deep recommendation system expertise with strong engineering execution and a passion for applying cutting-edge AI technologies to real-world products.

Requirements

5+ years of industry experience in: Machine Learning Engineering, Recommendation Systems, Personalization Platforms, Growth Engineering.
Experience building and operating recommendation systems at consumer internet scale serving millions of users.
Recommendation Systems Expertise: Strong experience with modern recommendation architectures, including: Collaborative filtering, Two-tower retrieval models, Sequential recommendation models, Graph Neural Networks (GNN), Multi-task and multi-objective learning (PLE, MMoE), Reinforcement learning, Contextual bandits.
Must have experience owning recommendation systems beyond individual model development, including architecture, deployment, experimentation, and business impact measurement.
Machine Learning & Statistics: Strong understanding of: Statistical learning, Experimentation methodologies, Causal inference, Treatment effect estimation.
Hands-on experience with: Uplift modeling, A/B testing, Conversion optimization, Growth measurement frameworks.
Programming & Data Engineering: Expert-level Python proficiency.
Strong proficiency in at least one additional language: Java, Scala, Go, C++.
Experience with modern machine learning frameworks: PyTorch, TensorFlow, JAX.
Strong experience with large-scale data processing technologies: Spark, Flink, Hive, MapReduce.
Distributed Systems & Infrastructure: Hands-on experience building large-scale ML systems using: Kafka, Spark Streaming, Flink, Feature stores (Feast, Tecton, or equivalent), Online serving infrastructure, Redis, Cassandra, Real-time recommendation architectures.
Communication & Collaboration: Strong verbal and written communication skills.
Ability to work effectively across Product, Engineering, Data Science, and Leadership teams.
Comfortable operating in a fast-paced, global environment.
Language Requirements: Fluent in both English and Mandarin Chinese.
Ability to collaborate directly with engineering and product teams across APAC.
Comfortable serving as a communication bridge between the US R&D Center and Asia-Pacific teams.

Nice To Haves

Experience in: Cryptocurrency, Web3, FinTech, Trading platforms.
Experience applying LLMs to recommendation and personalization systems.
Experience building hybrid recommendation and AI agent architectures.
Experience with: Multi-scenario joint modeling, User lifetime value prediction, Budget optimization, Operations research.
Experience building recommendation systems for social or community platforms, including: Feed ranking, Content personalization, Creator-user matching.
Publications in leading AI and machine learning conferences such as: KDD, NeurIPS, ICML, ICLR, WWW, SIGIR, WSDM, CIKM.
Experience helping establish engineering organizations, new product lines, or early-stage R&D teams.

Responsibilities

Build Personalized Recommendation Systems: Design and develop low-latency, real-time recommendation systems across web and mobile platforms. Drive personalization for: Trading product discovery, Campaign targeting, Content recommendation, Community feed ranking (ByX), User engagement experiences. Own the complete machine learning lifecycle, including: Data preparation, Feature engineering, Model development, Offline evaluation, Online experimentation, Production deployment.
Advance Recommendation & Personalization Algorithms: Design and implement state-of-the-art recommendation models, including: Two-tower retrieval architectures, Sequential recommendation models, Graph Neural Networks (GNN), Multi-task and multi-objective learning models (PLE, MMoE), Reinforcement learning and contextual bandits. Explore multi-scenario joint modeling to leverage signals across: Trading products, Community platforms, Marketing campaigns, User growth funnels.
Power AI-Driven Investment Experiences: Build the personalization layer behind TradeGPT’s AI investment assistant. Integrate: Portfolio signals, Trading behavior, Market intelligence, On-chain data, User preferences. Deliver: Personalized token recommendations, Intelligent market alerts, AI-driven investment insights, Agent-powered investment workflows. Research and implement hybrid recommendation architectures that combine: Traditional recommendation models, Large Language Models (LLMs), Agent-based AI systems.
Drive User Growth Through Machine Learning: Develop predictive models for: User churn, Reactivation likelihood, Upgrade propensity, Customer lifetime value (LTV). Apply causal inference and optimization techniques to improve growth outcomes, including: Uplift modeling, Difference-in-Differences (DiD), Treatment effect estimation, Resource allocation optimization. Optimize intervention timing, communication channels, and incentive strategies to maximize conversion efficiency.
Build User Lifecycle Intelligence: Develop a comprehensive user value and lifecycle framework. Identify behavioral signals that predict key milestones such as: First deposit, First trade, Product adoption, VIP upgrades. Design personalized engagement strategies that connect users with the most relevant products and experiences, including: Copy Trading, TradeGPT, Earn products, Campaigns and rewards. Measure and validate business impact through rigorous experimentation.
Own Experimentation & Measurement Systems: Design and enhance experimentation infrastructure supporting: Experiment assignment, Metrics pipelines, Statistical analysis, Self-service experimentation. Implement advanced experimentation methodologies including: CUPED, Sequential testing, Variance reduction techniques. Lead conversion lift studies and impact measurement initiatives to quantify recommendation system performance.
Build Scalable ML Infrastructure: Develop and maintain real-time and batch feature pipelines supporting recommendation and growth models. Partner with Data Engineering teams on: Feature store architecture, Data quality frameworks, Real-time data pipelines. Ensure production systems are highly observable, debuggable, and reliable at scale.
Technical Leadership: Collaborate closely with Product, Data Science, Community, TradeGPT, and Engineering teams. Translate business goals into scalable machine learning solutions. Establish engineering standards and best practices. Conduct design reviews and mentor junior engineers. Help scale the technical capabilities of the US R&D organization.