Machine Learning Engineer II, Fulfillment

Etsy•Brooklyn, NY

3d•Hybrid

About The Position

Etsy is hiring a Machine Learning Engineer II to join the Fulfillment ML team. This team owns the machine learning that powers Etsy's shipping and delivery experience, including models for accurate delivery estimates, seller pricing and shipping, and fulfillment decisions. The role combines ML platform engineering with hands-on applied ML work. On the platform side, responsibilities include building and operating pipelines, orchestration, and tooling for model training, validation, promotion, and inference. On the applied side, the engineer will partner with senior teammates on model evaluation, backtests, tuning, and readiness reviews, working deeply with existing models to grow applied ML expertise. This is an opportunity for a software engineer early in their ML career to develop skills in both systems and modeling within a mature MLOps environment.

Requirements

1-3 years of professional experience building and shipping production ML systems (internships and academic research projects that shipped can count).
Strong Python skills.
Good sense for code hygiene, testing, and reviewing work before it lands.
Some exposure to batch data pipelines.
Experience with ML orchestration (Airflow, Kubeflow, Dagster, Prefect, or similar).
Comfortable with SQL and at least one cloud data warehouse (BigQuery, Snowflake, Redshift) or ready to ramp quickly.
Understanding of the ML lifecycle, including training data, evaluation metrics, validation splits, and production deployment.
Ability to produce clear, testable, and maintainable code.
Eagerness to be mentored, receptiveness to feedback, and comfort growing inside an established codebase.
Mindfulness of the impact of work on Etsy buyers and sellers.

Nice To Haves

Prior experience with PyTorch or another deep learning framework.
Exposure to distributed compute (Spark, Ray, or Dask).
Experience contributing to orchestration or feature pipelines.
Prior experience in e-commerce, shipping, or logistics problem spaces.

Responsibilities

Build and maintain the training, validation, promotion, and batch-inference pipelines that put models into production and keep them healthy.
Write and extend Airflow DAGs within the MLOps framework for training, inference, and validation workflows across different environments.
Partner with teammates on applied ML tasks, including running backtests, tuning model outputs, and supporting seasonal readiness reviews.
Contribute to model migrations onto the internal ML platform by wiring up model configs, feature pipelines, postprocessors, and inference runners.
Triage and debug production incidents affecting model-driven surfaces and coordinate fixes with partner teams.
Improve observability through dashboards, retrain trending, data-quality tags, and alert hygiene.
Write clear PRs, design docs, and runbooks.
Take part in the team's on-call rotation for model-health and data-quality alerts.