Machine Learning Engineer

Job DescriptionSenior Machine Learning Engineer | Ad Tech Optimization\n\nML Scientist, AdTech\nLocation: Hybrid (Irvine, CA) or Fully Remote (CA, WA, AZ, NY, NJ, NV, UT, TX)\nCompensation: $200,000 $240,000 salary annually (solely base)\nIndustry: Mobile Gaming\n\nAbout the Role\nThe ML Scientist, AdTech will join a high-impact machine learning team responsible for designing, building, and iterating on the systems that power ad ranking, feature optimization, and model performance across the company's advertising platform. This person will work across the full ML lifecycle, from raw feature creation and engineering through model training, evaluation, and production deployment.\n\nKey Responsibilities\n\n Design and develop machine learning models focused on ad ranking, bidding optimization, and advertiser performance\n Drive end-to-end feature creation, feature engineering, and feature optimization for ranking and recommendation systems\n Build, train, evaluate, and iterate on neural network architectures and gradient-boosted models for production ad systems\n Develop and refine personalization systems and recommendation engines to optimize user value and engagement\n Collaborate with data engineering teams to build robust feature pipelines using Snowflake, OCI, and AWS infrastructure\n Conduct rigorous offline and online evaluation of model performance through experimentation and A/B testing\n Apply search and ranking algorithms to improve marketplace and ad auction performance\n Partner cross-functionally with product, engineering, and monetization teams to align ML outputs with business goals\n Continuously monitor and improve model accuracy, calibration, and scalability in production environments\n\n\nRequired Qualifications\n\n 5 or more years of experience in data science, machine learning, or applied ML in production environments\n Demonstrated experience with ad tech optimization, including ad ranking systems, bidding algorithms, or related advertising technology\n Hands-on experience with recommendation engines, personalization systems, or search and ranking algorithms\n Proven ability to design and configure neural network architectures for real-world ML applications\n Proficiency in Python and standard ML libraries (scikit-learn, TensorFlow, PyTorch, XGBoost/LightGBM)\n Experience working with OCI (Oracle Cloud Infrastructure), AWS, and Snowflake\n Strong foundation in feature engineering, feature selection, and model iteration best practices\n Solid understanding of CTR/CVR prediction, multi-task learning, and calibration techniques\n\n\nPreferred Qualifications\n\n Experience in mobile gaming, marketplace optimization, or user value optimization (LTV modeling, ROAS optimization)\n Familiarity with feature stores, online/offline feature serving, and training-serving skew mitigation\n Background in real-time bidding (RTB) systems or programmatic advertising platforms\n Experience with MLflow, Kubeflow, SageMaker, or Vertex AI for experiment tracking and model deployment\n