Machine Learning Engineer II, Fulfillment

Jobtailor; New York (NY); On-site; USD 120,000 - 170,000; Full time

Job summary

Jobtailor in New York is seeking an ML Engineer to build and maintain production pipelines for training, validation, promotion, and batch inference of ML models. You will craft Airflow DAGs within an MLOps framework across staging, shadow, and production environments.

Strong Python, code hygiene, testing, and SQL with cloud data warehouses are essential. PyTorch and distributed compute experience are a bonus; e-commerce/logistics exposure is valued.

Qualifications

• 1–3 years shipping production ML systems; internships count.
• Hones Python skills with production-grade code quality.
• Experience with batch data pipelines and ML orchestration tools.
• Familiar with SQL and cloud data warehouses (BigQuery/Snowflake/Redshift).
• Understanding ML lifecycle from data to deployment.
• PyTorch or similar DL framework is a plus.
• Experience in e-commerce, shipping, or logistics is a bonus.
• Ability to collaborate across teams with clear communication.

Responsibilities

• Build and maintain training, validation, promotion, and batch-inference pipelines for production ML models.
• Write and extend Airflow DAGs within the templatized MLOps framework across staging, shadow, and production environments.
• Run backtests and tune model outputs against business targets.
• Contribute to model migrations onto internal ML platforms and configurations.
• Triage and debug production incidents affecting model-driven surfaces.
• Coordinate fixes with partner teams.
• Improve observability through dashboards, data-quality tags, and alert hygiene.
• Write PRs, design documents, and runbooks.
• Participate in on-call rotation for model-health and data-quality alerts.
• Collaborate with engineers, data scientists, product managers, and designers.
• Develop ML systems supporting shipping-related signals.

Skills

Python

Airflow

SQL

Code hygiene

Batch data pipelines

ML lifecycle

PyTorch

Distributed compute

Tools

Airflow

BigQuery

Snowflake

Redshift

Dagster

Prefect

Kubeflow

Dagster

Dagster

Job description

• Build and maintain training, validation, promotion, and batch-inference pipelines for production ML models
• Write and extend Airflow DAGs within the templatized MLOps framework across staging, shadow, and production environments
• Run backtests, tune model outputs against business targets, and support seasonal readiness reviews
• Contribute to model migrations onto the internal ML platform, including model configurations, feature pipelines, postprocessors, and inference runners
• Triage and debug production incidents affecting model-driven buyer and seller surfaces
• Coordinate fixes with partner teams
• Improve observability through dashboards, retrain trending, data-quality tags, and alert hygiene
• Write PRs, design documents, and runbooks
• Participate in the on-call rotation for model-health and data-quality alerts, ramping gradually with senior support
• Partner with engineers, applied scientists, product managers, data scientists, designers, and product-facing engineering teams
• Develop machine learning systems supporting Etsy shipping, delivery estimates, shipping prices, fulfillment decisions, and delivery-risk signals

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 code hygiene, testing, and self-review practices
• Exposure to batch data pipelines
• Exposure to ML orchestration such as Airflow, Kubeflow, Dagster, Prefect, or similar
• Comfortable with SQL and at least one cloud data warehouse such as BigQuery, Snowflake, or Redshift, or able 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
• Prior experience with PyTorch or another deep learning framework is a bonus
• Exposure to distributed compute such as Spark, Ray, or Dask is a bonus
• Experience contributing to orchestration or feature pipelines is a bonus
• Prior experience in e-commerce, shipping, or logistics is a bonus
• Ability to collaborate and communicate effectively with teammates and multifunctional partners

Core Competencies

Demonstrates expertise in building and maintaining production ML systems, with strong proficiency in Python and experience in ML orchestration tools like Airflow. Capable of collaborating effectively with cross-functional teams while ensuring code quality and observability in machine learning pipelines.

Highest-signal resume keywords

• Production ML Systems Development
• Python Programming
• ML Orchestration (Airflow, Kubeflow)
• SQL and Cloud Data Warehousing
• Collaboration with Cross-Functional Teams

Hard Skills

• Machine Learning Systems
• Python
• SQL
• Batch Data Pipelines
• ML Lifecycle Understanding
• Code Hygiene
• Testing Practices
• PyTorch
• Distributed Compute (Spark, Ray)
• Feature Pipelines

Soft Skills

• Effective Communication
• Collaboration

Industry Keywords

• E-Commerce
• Shipping
• Logistics
• Model Health
• Data Quality

Tools & Technologies

• Airflow
• BigQuery
• Snowflake
• Redshift
• Dask
• Ray
• Dagster
• Prefect