Machine Learning Engineer

Remote with a preference on local. And if a local candidate is chosen, there may be an onsite requirement.

Job Summary

This role supports the development and modernization of the demand forecasting capabilities within the client's digital fulfillment organization. The team is responsible for forecasting order volumes, units, and fulfillment capacity across multiple channels (OPU, Ship-to-Home, Drive Up) to optimize store operations planning.

Working closely with data scientists and platform engineers, this role bridges ML research and production by scaling data processing workloads, building robust ML pipelines, and ensuring forecasting models run reliably at scale.

The ideal candidate brings an ML engineering mindset—combining data engineering, pipeline orchestration, and software engineering skills—to modernize a complex forecasting ecosystem that directly impacts store labor planning and customer experience.

Technical Skills: Must Have

Machine Learning & Data Science

Experience building and deploying ML models in production environments

Hands-on experience with time series forecasting (Prophet, ARIMA, or similar)

Understanding of hyperparameter tuning, model validation, and experiment tracking

Familiarity with feature engineering and feature store concepts

Data Engineering & Scalability

Proficiency converting pandas-based workloads to PySpark for large-scale processing

Experience with distributed data processing frameworks (Spark, Dask, or Ray)

Ability to optimize data pipelines for performance and cost efficiency

Working knowledge of data formats (Parquet, CSV) and partitioning strategies

Experience with BigQuery or similar analytical databases (table design, partitioning, clustering, writing/validating datasets)

ML Pipeline Orchestration

Experience building ML pipelines using Kubeflow Pipelines (KFP), Vertex AI, or Airflow

Understanding of pipeline component design, DAG orchestration, and caching strategies

Ability to integrate data validation, model training, and deployment steps into workflows

Experience with pipeline parameterization and configuration management

Software Engineering

Strong Python proficiency with production-grade coding standards

Ability to read, refactor, and extend existing codebases

Version control experience (Git) and structured change management

Familiarity with testing frameworks (pytest), dependency management (Poetry/UV), and code quality tools (pre-commit, linting)

Cloud & Infrastructure

Hands-on experience with GCP (Vertex AI, Cloud Storage) or equivalent cloud platforms

Familiarity with containerization (Docker) and container orchestration (Kubernetes)

Experience with CI/CD pipelines for ML workflows

Understanding of secrets management and environment configuration

Technical Skills: Nice to Have

Experience with Ray for distributed ML training and inference

Exposure to Hadoop ecosystem tools (Hive, HDFS, Spark on YARN)

Knowledge of ML model monitoring and drift detection

Experience with infrastructure-as-code (Terraform, Cloud Deployment Manager)

Familiarity with retail, supply chain, or demand forecasting domains

Experience working with data science teams to productionize research code

Background in scaling ML systems from prototype to enterprise-grade deployments

TECHNICAL SKILLS

Nice To Have

Exposure to ML/analytics-driven systems or forecasting platforms

Advanced performance tuning and scalability optimization experience

Familiarity with retail, merchandising, or supply chain systems

Experience supporting globally distributed teams across time zones

Knowledge of automated alerting, runbooks, and operational playbooks

Notes:

Remote

VIVA is an equal opportunity employer. All qualified applicants have an equal opportunity for placement, and all employees have an equal opportunity to develop on the job. This means that VIVA will not discriminate against any employee or qualified applicant on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, disability or protected veteran status