Lead Machine Learning Engineer

We are looking for a Lead Machine Learning Engineer to contribute to the evolution of AI and personalization capabilities of our online streaming platform. Working closely with senior experts, you will support the development and improvement of deep learning architectures.

We already have a production recommendation system and are now enhancing it within a more structured, multi-stage architecture while expanding into broader content and audience intelligence.

If you excel at applying advanced deep learning models in production environments and love to drive product impact through rigorous experimentation, we want you on our team.

Responsibilities:

• Architect & Scale: Contribute to the development and improvement of our recommendation system architecture (retrieval, ranking, and reranking) capable of serving millions of users.
• Power Dynamic Personalization: Develop algorithms and data-driven strategies to power dynamic carousels and real-time content discovery within defined product and system constraints
• Drive Experimentation: Apply and support existing experimentation frameworks to ensure your models translate into measurable product impact.
• Solve Core Streaming Challenges: Build multi-interest user representations and develop elegant solutions for platform-specific constraints like cold-starts, shared accounts, and mixed user intent leveraging established approaches and best practices
• Own and deliver specific components or modules within the ML pipeline, in alignment with broader system architecture: Collaborate closely with data and ML engineering teams to ensure your models are scalable, reliable, and seamlessly integrated into production.
• Innovate: by improving and extending existing methodologies, including content synergy analysis, audience behavior forecasting, and overall content intelligence.

Skills:

Core ML & Deep Learning Expertise

• Strong, proven experience building, improving, and deploying large-scale recommendation or personalization systems.
• Deep expertise in Deep Learning architectures, representation learning, and embedding spaces.
• Mastery of Python and standard deep learning frameworks, specifically PyTorch (or advanced TensorFlow).
• Strong mathematical foundation in linear algebra, probability, and optimization.

Experimentation & Evaluation

• Experience designing and running complex online A/B tests, primarily using established methodologies, understanding statistical significance, and connecting offline metrics to online success.
• Experience designing structured offline evaluation frameworks (NDCG, Recall, diversity, and personalization metrics), applied in practical contexts to proxy production impact

Practical Engineering & Deployment

• Experience deploying models: You don't just train models; you know what it takes to put them into production, monitor their health and debug them.
• Experience working with massive-scale behavioral datasets and implicit feedback modeling.
• Ability to reason practically about model behavior, bias, and edge cases (e.g., popularity bias, oversmoothing).

Nice to Have

• Graph Neural Networks: Exposure to or experience with GNN architectures for recommendation systems (e.g., LightGCN, GraphSAGE etc.).
• Online Learning: Familiarity with online learning paradigms and multi-armed bandits (e.g., Thompson Sampling, LinUCB).
• Cloud & MLOps: Experience with cloud ecosystems (Google Cloud Platform, BigQuery) and modern MLOps workflows.
• Domain Experience: Minimum 5 years in a similar role, with prior experience in the media, entertainment, or online streaming industry.