Role overview
ABOUT THE ROLE
FOX Corporation is looking for a SDE (L2), ML / Senior Engineer, ML to join the Personalization Recommendations (PnR) team and help drive the evolution of personalized content discovery across our streaming products. In this role, you ll be a hands-on contributor responsible for designing, building, and deploying ML models for recommendations, ranking, and semantic search , and ensuring they evolve through continuous learning and experimentation .
You will work at the intersection of ML model development, production engineering, and data-driven experimentation , collaborating with cross-functional teams to ensure scalable, performant, and personalized experiences. This role is ideal for engineers who have built and iterated on production-grade personalization systems and thrive on both deep technical challenges and business impact.
A SNAPSHOT OF YOUR RESPONSIBILITIES
- Design and build scalable recommendation and personalization models (ranking, re-ranking, user embeddings, semantic retrieval)
- Own the full model lifecycle: from data preparation , training , and evaluation , to versioning , deployment , and monitoring
- Develop and maintain continuous training loops and model refresh strategies for dynamic personalization
- Set up and interpret A/B experiments to optimize model performance and user engagement
- Collaborate with data engineers, MLOps teams, and product managers to ensure models integrate seamlessly into real-time and batch inference pipelines
- Leverage platforms like Databricks, MLflow , and feature stores to streamline model experimentation and reproducibility
- Apply LLMs and AI agents to improve personalization workflows and accelerate ML development pipelines
- Contribute to architecture decisions for personalization services and model serving infrastructure
- Mentor and provide technical guidance to junior data scientists and ML engineers , conducting code reviews, sharing best practices, and supporting their growth in areas such as model development, experimentation, and productionization
What we're looking for
- At least 3-7 years of experience in machine learning, applied data science , or related fields, with a strong focus on recommendation systems or personalization
- Demonstrated experience in developing and deploying ML models into production environments
- Deep understanding of ranking systems, user behavior modeling , and evaluation techniques (e.g., NDCG, AUC, MAP, CTR)
- Proficient in Python and ML libraries like PyTorch, TensorFlow , and frameworks such as Transformers or LightGBM
- Experience with Databricks , Spark, or similar big data platforms for large-scale model training and data processing
- Familiarity with model versioning, feature stores, experiment tracking , and MLflow
- Strong grasp of A/B testing design , analysis, and interpreting results for iterative model improvements
- Experience with LLM-based pipelines , semantic search , or vector similarity systems (e.g., FAISS, Vespa) is a plus
- Comfort working in cloud-native environments such as AWS or GCP
- Experience using or building AI agents , LangChain , or workflow automation frameworks for model experimentation
- Exposure to real-time inference systems and streaming architectures (Kafka, Flink)
- Experience working on personalization systems at scale , particularly for high-traffic applications or live events Contributions to open-source ML tools or research in personalization-related fields