Design and optimize large-scale recommendation algorithms to enhance personalized user experiences across feeds, content hubs, and interactive touchpoints.
Build intelligent content growth pipelines, including real-time hot topic detection, viral content diffusion modeling, and trending topic amplification.
Develop and integrate AIGC-aware recommendation systems, enabling dynamic ranking and generation strategies based on user preferences and market signals.
Apply state-of-the-art retrieval, ranking, and re-ranking models to refine recommendation precision, diversity, and freshness.
Leverage sequence models (Transformers, RNNs) and graph-based methods to model user behavior over time and across content types.
Employ multi-modal learning (text, image, video, social graphs) to improve understanding of content and boost personalization effectiveness.
Collaborate cross-functionally with product, data, and infrastructure teams to define and drive content growth strategies aligned with business objectives.
Run large-scale A/B tests, perform causal inference and behavioral analytics to quantify impact, guide iteration, and scale success.
Contribute to system architecture, model deployment pipelines, and performance optimization for real-time inference at scale.
Stay at the frontier of recommendation, generative AI, and content intelligence research, translating innovation into production impact.
Requirements:
5+ years of experience in recommendation systems, content AI, or growth-focused machine learning.
Proven track record in developing large-scale personalized recommendation engines using deep learning, collaborative filtering, or hybrid models.
Hands-on experience with hot topic mining, entity co-occurrence graph modeling, or event-based content surfacing is a strong plus.
Solid understanding of retrieval-ranking architectures, cold-start mitigation, and user lifecycle-based personalization.
Experience with deep learning frameworks (e.g., TensorFlow, PyTorch), vector search (e.g., FAISS, Milvus), and knowledge-enhanced models.
Proficiency in big data processing (Spark, Hive, Hadoop) and distributed computing frameworks.
Strong problem-solving and communication skills ability to drive cross-functional collaborations.
Passion for content ecosystems, user growth loops, and delivering measurable impact through intelligent systems.
Background in AIGC integration, content generation ranking, or LLM-based user interaction modeling.
Experience working in high-growth environments, social media, or consumer-facing recommendation platforms.
Familiarity with user engagement funnels, content virality metrics, and experimentation platforms (e.g., Optimizely, internal A/B infra).
Research exposure in causal inference, reinforcement learning, or multimodal retrieval.
