Lead Data Scientist w/ ML

Digitive; Vancouver; Hybrid; CAD 90,000 - 140,000; Full time

Job summary

An innovative firm is seeking a Lead Data Scientist with expertise in MLOps to spearhead the development of advanced machine learning systems in retail ecommerce. This pivotal role involves overseeing the architecture and operationalization of robust ML pipelines using cutting-edge tools like Databricks and MLflow, ensuring scalable and efficient solutions. The ideal candidate will have a rich background in data engineering and a passion for translating complex business needs into technical specifications. Join a dynamic team where your contributions will drive impactful change in the retail sector, fostering collaboration and innovation in a hybrid work environment.

Qualifications

• 10+ years in MLOps, data engineering, or ML infrastructure roles.
• Strong proficiency in Databricks, MLflow, and AWS or Azure.

Responsibilities

• Lead design of CI/CD pipelines for model training and deployment.
• Collaborate with teams to ensure enterprise-grade ML solutions.

Skills

MLOps

Data Engineering

Python

Databricks

MLflow

SQL

Terraform

Docker

Kubernetes

Airflow

Education

Bachelor's in Computer Science or related field

Master's in Data Science or related field

Tools

AWS

Azure

Git

Snowflake

Confluence

JIRA

Job description

Lead Data Scientist w/ ML

Get AI-powered advice on this job and more exclusive features.

Position Overview: We are seeking a Technical MLOps Lead to oversee the architecture, implementation, and operationalization of advanced forecasting models and machine learning systems within retail ecommerce. The ideal candidate will possess deep technical expertise in MLOps, data platforms, and model lifecycle management, combined with a strong understanding of demand forecasting, planning, and allocation use cases. This role involves leading the design, delivery, and optimization of robust ML pipelines utilizing Databricks, MLflow, Unity Catalog, and cloud-native tools on AWS or Azure, facilitating scalable, traceable, and cost-efficient ML solutions across the retail sector. Excellent communication and organizational skills are essential, with close collaboration with stakeholders.

ML Engineer Lead – Technical / Lead Data Scientist with ML experience

Location: Vancouver, BC (3 days in-office, Hybrid)

Experience: 12+ years

Key Responsibilities:

1. Lead the design of end-to-end CI/CD pipelines for model training, deployment, monitoring, and retraining using Databricks, MLflow, Unity Catalog, and Airflow.
2. Implement version control, model lineage, and governance practices aligned with enterprise architecture.
3. Drive infrastructure automation using Terraform, Docker, Kubernetes, and cloud-native services (SageMaker, Azure ML).
4. Optimize cost, performance, and scalability of ML pipelines and runtime environments.
5. Partner with data scientists, product owners, and business analysts to translate forecasting and planning requirements into scalable, reusable pipelines.
6. Support hierarchical time-series models, multi-location clustering, and demand prediction at SKU/location granularity.
7. Define monitoring metrics for model drift, accuracy decay, and business impact KPIs.
8. Lead the standardization of model lifecycle practices, including approvals, rollback strategies, and audit logging.
9. Manage and maintain a feature store for consistent reuse across models.
10. Collaborate with business, data engineering, and DevOps teams to ensure enterprise-grade solutions.
11. Mentor junior MLOps engineers and establish internal documentation, templates, and reusable components.
12. Translate user stories and epics into technical specifications and working pipelines.
13. Collaborate across agile squads to ensure timely delivery with high quality and traceability.
14. Lead incident resolution and RCA when ML models fail in production or regress in performance.
15. Drive post-deployment validation and facilitate user acceptance testing (UAT) for ML integrations.

Qualifications:

1. 10+ years of experience in MLOps, data engineering, or ML infrastructure roles.
2. Strong proficiency in Databricks, MLflow, Unity Catalog, Airflow, and feature store solutions.
3. Programming proficiency in Python and PySpark for building reusable ML components and ETL flows.
4. Proven success in operationalizing ML models for forecasting, planning, or optimization in retail or e-commerce.
5. Experience with AWS (S3, EC2, EKS, SageMaker) or Azure (ML Studio, Synapse, AKS).
6. Strong skills in SQL for data analysis, ETL validation, and reporting (Snowflake/Databricks preferred).
7. Hands-on experience with CI/CD pipelines, GitOps, and infrastructure-as-code (Terraform, CloudFormation).
8. Familiarity with containerization (Docker), orchestration (Kubernetes), and observability tools (Grafana, Prometheus, ELK).
9. Ability to author technical documentation and translate business needs into MLOps architecture.

Nice to Have:

• Experience with demand forecasting, inventory optimization, or promotion effectiveness in retail.
• Familiarity with Agile/Scrum processes and tools (JIRA, Confluence, ServiceNow).
• Exposure to data science workflows, including model explainability and bias detection.
• Understanding of data governance, security, and compliance in enterprise ML systems.

Seniority level

• Mid-Senior level

Employment type

• Full-time

Job function

• Information Technology

Industries

• Staffing and Recruiting