Senior ML Engineer - Production ML on GCP & BigQuery Remote

Andersen Lab; United States; Remote; USD 150,000 - 190,000; Full time

Benefits offered by this job

Private health insurance

Annual bonus

Company training portal

Referral program

Remote/hybrid options

Job summary

Ulvior is seeking an experienced Machine Learning Engineer in the United States to design, deploy, and maintain production-grade ML models using Python and gradient boosting.

You will own feature engineering in BigQuery, data validation, model calibration, and integration with external APIs. Remote/hybrid options are available with strong emphasis on scalable pipelines and cross-functional collaboration.

Qualifications

• Hands-on ML engineering in production environments.
• Proven experience with gradient boosting and hyperparameter tuning.
• Strong SQL and BigQuery data engineering capabilities.
• Experience deploying ML workloads on GCP (Vertex AI, Cloud Run, Pub/Sub).
• Understanding of model calibration and loss functions.
• Experience integrating ML outputs with APIs and external systems.

Responsibilities

• Develop, deploy, and maintain production-grade ML models in the cloud.
• Lead feature engineering in BigQuery and maintain Gold/Silver data layers.
• Monitor model drift, conduct A/B testing, and ensure data quality.
• Build scalable ML pipelines with Airflow, Vertex AI, and Cloud Run.
• Collaborate with advertising platforms and pricing/bidding systems.

Skills

Python ML

XGBoost

CatBoost

LightGBM

SQL

BigQuery

GCP

Vertex AI

Airflow

Cloud Run

CI/CD

A/B testing

Bayesian stats

Feature engineering

Identity resolution

Model calibration

LTV modeling

RFM analytics

Tools

Terraform

Docker

GitHub Actions

BigQuery ML

Job description

Ulvior is seeking an experienced Machine Learning Engineer in the United States to design, deploy, and maintain production-grade ML models using Python and gradient boosting.

You will own feature engineering in BigQuery, data validation, model calibration, and integration with external APIs. Remote/hybrid options are available with strong emphasis on scalable pipelines and cross-functional collaboration.