Senior Data Scientist – ML Classification & Content Safety

Tasks

• Build and maintain training data pipelines
• Build labeled evaluation datasets with annotation workflows
• Collaborate with engineering on latency and reliability constraints
• Connect offline evaluation to production monitoring
• Detect classification drift and error patterns
• Drive content classification evaluation methodology
• Integrate model outputs into production filtering stack
• Investigate misclassification errors with root cause analysis
• Maintain model cards with metrics and confusion matrices
• Mentor data science team on applied ML rigor
• Participate in on call incident lifecycle and retrospectives
• Prototype model improvements with active learning and domain adaptation
• Refactor binary models to multiclass and multilabel classification

Perks/Benefits

• N/A

Skills/Tech-stack

A/B | A/B Testing | AWS SageMaker | Active Learning | Annotation Workflows | B testing | Class imbalance | Cloud ML | Confusion matrix | Data Pipelines | Data Versioning | Data cleaning | Domain Adaptation | Experiment tracking | Google Cloud | Google Cloud Vertex | Google Cloud Vertex AI | Language Processing | Machine Learning | Model Cards | Model Deployment | Model Evaluation | Multiclass Classification | Multilabel Classification | Natural Language | Natural Language Processing | NumPy | Pandas | Precisión | PyTorch | Python | Recall | Reproducible Research | Scikit-learn | TF-IDF | TensorFlow | Text Mining | Training Data Pipelines | Training data | Vertex AI