About the job
Modeling Expertise:
- Proven experience in designing and implementing propensity models focused on cross-selling and upselling opportunities.
- In-depth knowledge of Next Best Action / Next Best Offer systems.
- Solid understanding of supervised learning methodologies, uplift modeling, and causal inference techniques.
Programming & Engineering:
- Proficient in Python (required); knowledge of R or Scala is advantageous.
- Experience with distributed computing frameworks such as Spark, Dask, or Ray.
- Skilled in developing production-level ML pipelines using tools like Airflow, MLflow, or Kubeflow.
- Strong familiarity with software engineering best practices including version control, CI/CD, and thorough testing.
Data Infrastructure:
- Experience with cloud platforms (AWS/GCP/Azure) and data warehouses (Snowflake, BigQuery, Redshift).
- Excellent SQL skills; adept at optimizing queries and handling large datasets.
MLOps & Deployment:
- Proven ability to deploy models to production using APIs or streaming technologies (Kafka, Flink).
- Experienced in model versioning, experiment management, and deployment practices with MLflow, SageMaker, or Vertex AI.
Monitoring & Observability:
- Capable of establishing model monitoring, drift detection, and alerting systems utilizing Prometheus, Grafana, Evidently, or custom dashboards.
- Familiarity with logging frameworks and performance profiling for ML services.
GenAI (Preferred):
- Experience with Large Language Models, embeddings, prompt engineering, and vector databases (e.g., FAISS, Pinecone).
- Ability to incorporate GenAI into decision-making systems or customer-facing applications.
Leadership & Collaboration:
- Proven leadership skills to guide senior data scientists while maintaining a hands-on approach.
- Adept at collaborating with product managers, engineers, and business stakeholders.
