Principal Machine Learning Engineer, Recommendation Algorithm

About the Role

As a Principal Recommendation Algorithm Engineer, you will be responsible for personalized recommendations across the trading products, content, and community. You will understand how user behavior evolves across scenarios; model cross-scenario behavior sequences, short- and long-term interests, and changes in intent; and jointly optimize objectives such as clicks, conversions, and retention to improve recommendation performance and user experience.

You will work closely with recommendation engineering, growth product and operations, and data science teams to build a high-throughput, low-latency, highly available personalization system serving more than 80 million users globally. You will drive technical advances in personalized recommendations, distribution strategies, user understanding, and content understanding.

Key Responsibilities

• Develop and improve recommendation models for the trading products, content, and community. Use large-scale user behavior data to model user interests accurately and improve recommendation performance and user experience.
• Explore cross-domain transfer and cold-start optimization across business scenarios, taking each scenario's characteristics into account to improve cross-scenario recommendation results and cold-start coverage.
• Optimize multi-objective ranking models for CTR, CVR, LTV, and other outcomes. Design mechanisms for combining ranking objectives and balance clicks, conversions, and long-term value under scenario-specific constraints.
• Model cross-scenario user behavior sequences, short- and long-term interests, and changes in intent. Develop reusable user representations to address scenario transfer, sparse feedback, and cold-start challenges.
• Explore generative recommendation approaches, including semantic IDs and generative candidate generation, and integrate generative methods with discriminative recommendation pipelines.

Major Requirements

• At least 4 years of experience developing search, advertising, or recommendation algorithms at a consumer-facing internet company, with a deep understanding of retrieval, ranking, and multi-objective modeling.
• Strong computer science fundamentals and proficiency in at least one of Python, Java, or C++. You write well-structured code, apply sound design principles, and enjoy tackling challenging problems.
• Strong analytical and logical thinking, with the ability to identify problems and opportunities in data.
• An interest in emerging technologies and the ability to approach challenging problems with clarity and sound reasoning.
• Good business judgment and communication skills, with the ability to collaborate on and solve business problems.

Nice-to-have:

• Search, advertising, or recommendation algorithm experience at major technology companies
• Experience with multi-objective modeling, short- and long-term user sequence modeling, personalized uplift modeling, or generative modeling.
• Publications at leading international conferences, including but not limited to KDD, SIGIR, RecSys, ACL, or NeurIPS.
• An AI-driven approach and hands-on experience bringing LLM or agent applications into production for search, advertising, or recommendation use cases.

Why Join Us

• A multi-domain recommendation challenge in fintech: Go beyond a single domain such as video or e-commerce. You will build personalization capabilities across trading products, market intelligence, community content, campaigns, and AI-powered investment workflows.
• Proven business impact with substantial room for ML advancement: Our current recommendation system has demonstrated a 71% increase in CTR and a 1,285% increase in conversion rate, with significant potential for an ML-native upgrade.
• Work at the intersection of AI and recommendations: Build where traditional recommender systems, generative AI, and LLM agents meet—one of the most active frontiers in engineering.
• An opportunity to lead, not just follow: Our combination of trading, content, community, AI, and campaigns creates distinctive technical challenges and enables rapid iteration.
• Global scale: Serve more than 80 million users across over 200 countries, tackling the real-world complexity of large-scale, real-time systems.