Staff ML Engineer - Ranking Systems Lead (Hybrid)

Taskrabbit; San Francisco (CA); Hybrid; USD 170,000 - 225,000; Full time

Benefits offered by this job

Health insurance

401k match (US)

Generous PTO and company-wide closures

Job summary

Taskrabbit is seeking a Staff Machine Learning Engineer to own and evolve the core ranking system that drives every matching request. You’ll lead architecture, design, and production reliability while collaborating with Product, Data Science, Risk, and Commerce teams.

You will mentor engineers, drive scalable ML infrastructure, and address biases with a focus on improving personalization and conversion across a hybrid US-based team.

Qualifications

• 8+ years of industry experience building and deploying production-grade ML systems with end-to-end ownership.

Responsibilities

• Own the architecture, model design, experiment strategy, and production reliability of the core ranking system end-to-end.
• Serve as the primary technical contact for Product, Data Science, Risk, and Commerce on matching and ranking.
• Build automated retraining pipelines and monitoring to prevent model drift and enable safe experimentation.
• Address biases in ranking, improve data quality for training, and drive better conversion.
• Leverage client intent signals and personalization to optimize booking outcomes.
• Mentor junior engineers and raise the technical bar through reviews and guidance.
• Shape long-term ML architecture and make build-vs-buy recommendations.

Skills

Python

SQL

PyTorch

TensorFlow

scikit-learn

LightGBM/XGBoost

Kafka

Airflow

Snowflake/BigQuery

Docker/Kubernetes

dbt

Education

BS/MS/PhD in Computer Science, Statistics, OR related quantitative field

Tools

Kafka

Airflow

Snowflake/BigQuery

Docker/Kubernetes

dbt

Job description

Taskrabbit is seeking a Staff Machine Learning Engineer to own and evolve the core ranking system that drives every matching request. You’ll lead architecture, design, and production reliability while collaborating with Product, Data Science, Risk, and Commerce teams.

You will mentor engineers, drive scalable ML infrastructure, and address biases with a focus on improving personalization and conversion across a hybrid US-based team.