Data Scientist, Adtech (Bengaluru)

As a Data Scientist in the advertising technology division, your primary responsibility will be to design and implement machine learning models and optimization algorithms to enhance ad delivery efficiency and maximize campaign outcomes. This role requires you to take ownership of the entire process, starting from formulating hypotheses and engineering features to deploying and continuously improving the models in production environments. Key Responsibilities: - Define optimization problems for ad delivery and establish key performance indicators (KPIs), metrics, and monitoring dashboards. - Perform data preprocessing, feature engineering, and model development for tasks such as price optimization, click-through rate (CTR) and conversion rate (CVR) prediction, and creative performance analysis. - Conduct offline evaluations and simulations, followed by online deployment and A/B testing strategies. - Implement MLOps practices including training/inference pipelines, drift detection, automated rollback, and governance for quality and privacy. - Collaborate with product, engineering, and operations teams to translate business requirements into actionable data solutions. Technical Environment: - Cloud-based infrastructure (e.g., GCP or equivalent). - Big data tools (BigQuery, Dataflow, Pub/Sub). - Distributed systems and real-time processing. - Programming languages: Python, Go. - Infrastructure automation: Terraform, Ansible. Mandatory Qualifications: - 3+ years of experience in data analysis and machine learning using Python and SQL. - Proficiency with libraries such as Pandas, NumPy, scikit-learn, and visualization tools. - Hands-on experience with large-scale data processing (Spark, BigQuery) and reproducible analytics workflows. - Solid foundation in statistics, probability, and experimental design (A/B testing, causal inference). - Experience building and deploying ML models (regression, classification, tree-based methods, basic neural networks) with robust evaluation strategies. - Knowledge of digital advertising concepts (CTR/CVR prediction, bidding strategies, KPI optimization) or similar optimization domains. - Practical experience in production ML systems, including monitoring and drift detection. - Excellent communication skills for stakeholder collaboration and presenting analytical insights. - Degree in Computer Science, Statistics, Applied Mathematics, or related field. - Fluent English (TOEIC 800+ or equivalent). Preferred Qualifications: - Understanding of ad auction mechanisms (first-price/second-price, bid shading, reserve price optimization). - Experience with advanced optimization techniques (Bayesian optimization, multi-armed bandits, reinforcement learning). - Familiarity with creative optimization and generative AI for ad content. - Knowledge of real-time streaming platforms (Kafka, Flink, Beam) and online inference systems. - MLOps best practices (feature stores, CI/CD, containerization, monitoring). - Cloud experience with GCP, AWS, or Azure. As a Data Scientist in the advertising technology division, your primary responsibility will be to design and implement machine learning models and optimization algorithms to enhance ad delivery efficiency and maximize campaign outcomes. This role requires you to take ownership of the entire process, starting from formulating hypotheses and engineering features to deploying and continuously improving the models in production environments. Key Responsibilities: - Define optimization problems for ad delivery and establish key performance indicators (KPIs), metrics, and monitoring dashboards. - Perform data preprocessing, feature engineering, and model development for tasks such as price optimization, click-through rate (CTR) and conversion rate (CVR) prediction, and creative performance analysis. - Conduct offline evaluations and simulations, followed by online deployment and A/B testing strategies. - Implement MLOps practices including training/inference pipelines, drift detection, automated rollback, and governance for quality and privacy. - Collaborate with product, engineering, and operations teams to translate business requirements into actionable data solutions. Technical Environment: - Cloud-based infrastructure (e.g., GCP or equivalent). - Big data tools (BigQuery, Dataflow, Pub/Sub). - Distributed systems and real-time processing. - Programming languages: Python, Go. - Infrastructure automation: Terraform, Ansible. Mandatory Qualifications: - 3+ years of experience in data analysis and machine learning using Python and SQL. - Proficiency with libraries such as Pandas, NumPy, scikit-learn, and visualization tools. - Hands-on experience with large-scale data processing (Spark, BigQuery) and reproducible analytics workflows. - Solid foundation in statistics, probability, and experimental design (A/B testing, causal inference). - Experience building and deploying ML models (regression, classification, tree-based methods, basic neural netw