Data Scientist - Machine Learning - AWS

Role Overview: You will be responsible for building and shipping ML models end-to-end in various areas such as personalization, ranking, propensity scoring, fraud detection, and pricing. Additionally, you will collaborate with product and engineering teams to identify high-leverage ML opportunities tied to business metrics. Wrangling large structured and unstructured datasets, building reliable features and data pipelines, designing and running A/B tests and experiments, and building monitoring for model drift, data quality, and business KPIs will also be part of your role. Clear communication of findings to technical and non-technical stakeholders and contribution to data infrastructure and best practices across the team are essential responsibilities. Key Responsibilities: - Build and ship ML models end-to-end in areas like personalization, ranking, propensity scoring, fraud detection, and pricing - Partner with product and engineering teams to identify high-leverage ML opportunities tied to business metrics - Wrangle large structured and unstructured datasets; build reliable features and data pipelines - Design and run A/B tests and experiments with clear success metrics - Build monitoring for model drift, data quality, and business KPIs - Communicate findings clearly to technical and non-technical stakeholders - Contribute to data infrastructure and best practices across the team Qualifications Required: - 2-6 years of data science or ML experience, ideally with models shipped to production - Strong Python and SQL skills; familiarity with Git, Docker, and CI/CD - Hands-on experience with ML frameworks: Scikit-learn, XGBoost, PyTorch, or TensorFlow - Experience with cloud platforms (AWS or GCP) and data warehouses (Redshift or BigQuery) - Solid grasp of model evaluation, feature engineering, and experiment design - Exposure to recommender systems, NLP, anomaly detection, or time-series is a plus - Experience with BI and visualization tools such as Looker or Tableau is a plus Additional Details: The company is looking for candidates who are proficient in using various skills and tools such as Python, SQL, Scikit-learn, XGBoost, PyTorch/TensorFlow, AWS/GCP, BigQuery/Redshift, A/B testing, feature engineering, model deployment, Docker, Looker/Tableau. Role Overview: You will be responsible for building and shipping ML models end-to-end in various areas such as personalization, ranking, propensity scoring, fraud detection, and pricing. Additionally, you will collaborate with product and engineering teams to identify high-leverage ML opportunities tied to business metrics. Wrangling large structured and unstructured datasets, building reliable features and data pipelines, designing and running A/B tests and experiments, and building monitoring for model drift, data quality, and business KPIs will also be part of your role. Clear communication of findings to technical and non-technical stakeholders and contribution to data infrastructure and best practices across the team are essential responsibilities. Key Responsibilities: - Build and ship ML models end-to-end in areas like personalization, ranking, propensity scoring, fraud detection, and pricing - Partner with product and engineering teams to identify high-leverage ML opportunities tied to business metrics - Wrangle large structured and unstructured datasets; build reliable features and data pipelines - Design and run A/B tests and experiments with clear success metrics - Build monitoring for model drift, data quality, and business KPIs - Communicate findings clearly to technical and non-technical stakeholders - Contribute to data infrastructure and best practices across the team Qualifications Required: - 2-6 years of data science or ML experience, ideally with models shipped to production - Strong Python and SQL skills; familiarity with Git, Docker, and CI/CD - Hands-on experience with ML frameworks: Scikit-learn, XGBoost, PyTorch, or TensorFlow - Experience with cloud platforms (AWS or GCP) and data warehouses (Redshift or BigQuery) - Solid grasp of model evaluation, feature engineering, and experiment design - Exposure to recommender systems, NLP, anomaly detection, or time-series is a plus - Experience with BI and visualization tools such as Looker or Tableau is a plus Additional Details: The company is looking for candidates who are proficient in using various skills and tools such as Python, SQL, Scikit-learn, XGBoost, PyTorch/TensorFlow, AWS/GCP, BigQuery/Redshift, A/B testing, feature engineering, model deployment, Docker, Looker/Tableau.