Staff Machine Learning Engineer - Retention
About this role
Data-driven engineers with a background in marketplaces and a focus on customer retention will thrive in this position at Taskrabbit. The team builds core ranking systems and customer retention strategies designed to deepen user relationships, increase repeat purchase frequency, and unlock new revenue streams within the existing customer base. Working across the full machine learning lifecycle, the person in this role will take charge of feature engineering, model development, production deployment, and infrastructure scaling to drive repeat engagement and lifetime value growth. The position exists to capture significant untapped potential by optimizing the post-first-job experience through intelligent matching, personalized recommendations, and dynamic pricing.
What you will do
- Manage the reliability and performance of the core ranking system to ensure accurate tasker-to-job matching.
- Drive repeat purchase frequency and customer lifetime value using intelligent matching, personalized recommendations, and category discovery.
- Reduce customer churn and friction by implementing predictive quality interventions and proactive customer success strategies.
- Own the complete machine learning lifecycle ranging from feature engineering and training to evaluation, deployment, and production monitoring.
- Build and maintain scalable machine learning infrastructure and data pipelines that support real-time, near real-time, and batch contexts.
- Collaborate closely with engineering and science teams to optimize algorithms for training, inference, and evaluation.
- Write clean, maintainable code and participate actively in code reviews and engineering best practices.
What you need
- Hold a Bachelor of Science, Master of Science, or PhD in Computer Science, Statistics, Operations Research, or a related quantitative field.
- Bring 8 or more years of industry experience in building and deploying high-quality, production-grade machine learning models and systems.
- Demonstrate strong theoretical knowledge and hands-on expertise in search, ranking, recommender systems, pricing or elasticity modeling, or predictive analytics.
- Possess solid software engineering skills with proficiency in programming languages such as Python.
- Show hands-on experience with popular machine learning libraries including Scikit-learn, lightgbm, xgboost, TensorFlow, and PyTorch.
- Demonstrate proficiency in SQL for writing complex queries and transforming data.
- Have experience building REST API-based services and working with modern data technologies like Docker, Kubernetes, Kafka, Airflow, and data warehouses.
Nice to have
- Familiarity with dbt for transforming and testing data
- Familiarity with Infrastructure as Code tools such as Github actions and CI/CD pipelines
- Experience working in marketplace or platform contexts where ranking, matching, and pricing impact user experience and business outcomes
Benefits
- Employer-paid health insurance
- 401k match with immediate vesting for US-based employees
- Generous and flexible time off with 2 company-wide closure weeks
- Taskrabbit product stipends
- Wellness, productivity, and education stipends
- IKEA discounts and reproductive health support
Skills and tech stack
Questions candidates ask
What is the remote policy for this role?
Taskrabbit operates as a hybrid company with employees distributed across the US and EU. This role requires working 2 days in the office at either the San Francisco or New York City hub every Tuesday and Wednesday.
What is the compensation range for the position?
The base pay range for this position is $170,000 to $225,000. Total compensation also consists of a company bonus, benefits, and perks, with final offer amounts determined by relevant experience, qualifications, geography, and level.
What technologies and tools will I be working with?
The tech stack includes Python, SQL, machine learning libraries like Scikit-learn, lightgbm, xgboost, TensorFlow, and PyTorch, along with infrastructure and data tools such as Docker, Kubernetes, Kafka, Airflow, data warehouses, and dbt.
What does the team and culture look like?
The culture is collaborative, pragmatic, and fast-paced, celebrating innovation, inclusion, and hard work. Employees are surrounded by talented, supportive, smart, and kind leaders and teams.