À propos
ML models for fraud detection
using various techniques including supervised, unsupervised, and deep learning.
Conduct
exploratory data analysis (EDA)
to identify anomalies and emerging fraud patterns.
Create and manage
end-to-end MLOps pipelines
on GCP and Vertex AI, focusing on training, evaluation, deployment, and monitoring.
Collaborate with cross-functional teams including
Engineering, Data Engineering, Investigations, and Product
to implement fraud models and develop prevention strategies.
Research and prototype new detection techniques, such as
LLMs, anomaly detection, and behavioral modeling .
Lead technical design reviews, mentor junior team members, and uphold best practices through robust code reviews and technical discussions.
Maintain comprehensive documentation and model governance to ensure reliability and scalability across the ML platform.
Tech Stack & Tools Languages:
Python, SQL
Frameworks:
TensorFlow, PyTorch, Scikit-learn
Data & Platforms:
GCP, Vertex AI, PySpark, BigQuery, Hadoop, Hive
MLOps & Automation:
MLflow, Airflow, CI/CD frameworks
Collaboration:
GitHub, JIRA, partnerships with Engineering, Data Platform, and Fraud Investigations
Experience & Qualifications Advanced degree (Master's or PhD) in a related field such as Computer Science, Data Science, Statistics, or Mathematics.
5-8 years of hands-on experience in
data science, ML engineering, or applied machine learning , with a successful track record in developing and deploying ML models.
Proven ability to build, scale, and deploy
production ML models .
Strong experience in
MLOps and pipeline automation
on cloud platforms (GCP / Vertex AI preferred).
Proficient in data cleaning and preprocessing techniques to ensure high-quality training data.
Experience in
fraud detection, anomaly detection, or risk modeling
is a plus but not required.
Excellent programming and collaboration skills, adept at bridging gaps between data science, engineering, and business.
Familiarity with deep learning architectures like CNNs, GANs, and transformers.
Expertise in tuning hyperparameters to optimize model performance.
Evaluate model performance using key metrics and conduct error analysis for optimization.
Strong problem-solving skills and a passion for addressing real-world challenges through a data-driven approach.
Outstanding communication abilities, capable of conveying data-driven stories through visualizations and narratives.
A collaborative team player, capable of working effectively across different geographies and time zones.
This position will operate as a
Hybrid/Flex for Your Day
work arrangement based at Target HQ in Minnesota. A Hybrid/Flex for Your Day arrangement allows for a combination of onsite and virtual work based on team needs. Work duties cannot be performed outside of the primary work location unless specified by Target. Our commitment to diversity means that all applicants with disabilities will receive reasonable accommodations in the application or interview process. Please reach out if any accommodations are needed.
Compétences linguistiques
- English
Avis aux utilisateurs
Cette offre provient d’une plateforme partenaire de TieTalent. Cliquez sur « Postuler maintenant » pour soumettre votre candidature directement sur leur site.