Data Science / Data Engineer

Cortance looking for a Senior Data Science / Data Engineer to join a project involving a large-scale legacy data migration into a modern warehouse, followed by ongoing pipeline ownership and analytics support.

What you'll do

• Migrate data from legacy databases/warehouses into a modern cloud platform — schema mapping, transformation logic, validation, and cutover;
• Design, build, and maintain batch and streaming data pipelines that feed models, dashboards, and downstream products;
• Design and optimize warehouse/lakehouse schemas and queries;
• Run exploratory analysis, statistical modeling, and experiments to answer specific business questions;
• Prepare, version, and serve training data and features for ML teams;
• Use AI coding tools (Claude Code, Codex, Copilot, etc.) to speed up pipeline development, testing, and documentation;
• Report findings clearly to non-technical stakeholders.

Requirements

Modeling & core skills

• 5+ years of hands-on experience in data science / ML engineering, with models built and shipped for real business problems — predictive modeling and forecasting, classification, clustering, anomaly detection, recommendation engines, or NLP;
• Strong Python, with deep working knowledge of scikit-learn, XGBoost, LightGBM, and Pandas;
• Practical experience with PyTorch or TensorFlow for deep learning workflows;
• Solid statistics fundamentals;
• Experience with LLMs, RAG systems, or LangChain for generative AI applications is a strong plus.

Production ownership

• Proven ability to own the full pipeline;
• Experience writing Dockerfiles and setting up CI/CD for ML workloads;
• Hands-on experience with model versioning and experiment tracking (DVC, MLflow, or equivalents);
• Experience monitoring deployed models for drift and degradation;
• Practical experience with data pipeline tools (Airflow, dbt, Spark, or equivalents) and cloud data platforms (BigQuery, Snowflake, Redshift, or similar);
• Experience with at least one major cloud provider (AWS, GCP, or Azure) for data storage, processing, and model deployment.