Key Responsibilities:
- Design and implement robust anomaly detection models for structured and unstructured data.
- Analyze large datasets to identify trends, patterns, and outliers.
- Develop scalable solutions for real-time and batch anomaly detection.
- Collaborate with data engineers, product managers, and business stakeholders to define problem statements and deliver actionable insights.
- Evaluate and compare different algorithms (e.g., Isolation Forest, Autoencoders, One-Class SVM, etc.) for anomaly detection.
- Monitor model performance and continuously improve accuracy and efficiency.
- Document methodologies, experiments, and results for internal and external stakeholders.
Required Qualifications:
- Bachelor’s or Master’s degree in Computer Science, Statistics, Mathematics, or a related field.
- 3+ years of experience in data science or machine learning roles.
- Proven experience in building and deploying anomaly detection systems.
- Proficiency in Python (NumPy, pandas, scikit-learn, TensorFlow/PyTorch).
- Strong understanding of statistical methods, time-series analysis, and unsupervised learning techniques.
- Experience with data visualization tools (e.g., Matplotlib, Seaborn, Plotly).
- Familiarity with cloud platforms (AWS, GCP, or Azure) and big data tools (Spark, Hadoop) is a plus.
Preferred Skills:
- Experience with streaming data and real-time anomaly detection (e.g., Kafka, Flink).
- Knowledge of domain-specific anomaly detection use cases (e.g., fraud detection, system monitoring, IoT).
- Strong communication skills and ability to explain complex models to non-technical stakeholders.
Key Responsibilities:
- Design and implement robust anomaly detection models for structured and unstructured data.
- Analyze large datasets to identify trends, patterns, and outliers.
- Develop scalable solutions for real-time and batch anomaly detection.
- Collaborate with data engineers, product managers, and business stakeholders to define problem statements and deliver actionable insights.
- Evaluate and compare different algorithms (e.g., Isolation Forest, Autoencoders, One-Class SVM, etc.) for anomaly detection.
- Monitor model performance and continuously improve accuracy and efficiency.
- Document methodologies, experiments, and results for internal and external stakeholders.
Required Qualifications:
- Bachelor’s or Master’s degree in Computer Science, Statistics, Mathematics, or a related field.
- 3+ years of experience in data science or machine learning roles.
- Proven experience in building and deploying anomaly detection systems.
- Proficiency in Python (NumPy, pandas, scikit-learn, TensorFlow/PyTorch).
- Strong understanding of statistical methods, time-series analysis, and unsupervised learning techniques.
- Experience with data visualization tools (e.g., Matplotlib, Seaborn, Plotly).
- Familiarity with cloud platforms (AWS, GCP, or Azure) and big data tools (Spark, Hadoop) is a plus.
Preferred Skills:
- Experience with streaming data and real-time anomaly detection (e.g., Kafka, Flink).
- Knowledge of domain-specific anomaly detection use cases (e.g., fraud detection, system monitoring, IoT).
- Strong communication skills and ability to explain complex models to non-technical stakeholders.