Machine Learning Engineer, Offline Risk

Airbnb was born in 2007 when two Hosts welcomed three guests to their San Francisco home, and has since grown to over 4 million Hosts who have welcomed more than 1 billion guest arrivals in almost every country across the globe. Every day, Hosts offer unique stays and experiences that make it possible for guests to connect with communities in a more authentic way.

The Community You Will Join:

At Airbnb, we believe in creating a world where anyone can belong anywhere. The Trust Offline Risk team is pivotal in ensuring their safety and support throughout the entire Airbnb experience. As part of this team, you will design and build scalable, robust systems to detect and mitigate safety risks, collaborating closely with product, data science, and operations teams to maintain Airbnb as a safe and trusted community.

The Difference You Will Make:

Your work on the Offline Risk team will directly impact the safety of Airbnb users worldwide. By building real-time risk detection services and developing advanced machine learning models, you will help us stay ahead of evolving threats. Your contributions will ensure that our platform remains secure and trustworthy, making a tangible difference in the lives of our hosts and guests.

A Typical Day: 

As a machine learning engineer in Trust, your contributions will span a variety of shapes:

• Work with large-scale structured and unstructured data to build and continuously improve cutting-edge machine learning models for Airbnb’s product, business, and operational use cases. Some recent works include:
  
  • Supervised model ensembles that include multiple DNNs and graph-based models
  • Contextual Decision engine 
  • Unsupervised clustering models for natural language understanding
  • LLM experimentation with label taxonomy and manual agent automation
  • Optimizing ranking algorithms for search
• Collaborate with a wide variety of business functions to predict and prevent physical safety and property damage incidents.
• Develop new holistic machine learning model detection strategies by partnering with other teams across the Trust Organization.
• Work collaboratively with cross-functional partners, including software engineers, data scientists, product managers, and operations to identify opportunities for business impact, and refine and prioritize requirements for fraud detection and mitigation.
• Hands-on develop, productionize, and operate machine learning models and pipelines at scale, including both batch and real-time use cases.
• Enhance and extend risk investigation tools to enable efficient decision-making on behaviors that could result in physical safety or property damage incidents.
• Create products to deter bad actors and restrict their usage on the platform.
• Provide and educate on guest and host safety standards to mitigate vulnerabilities.

Your Expertise:

• 2+ years of industry experience in applied machine learning, including a MS or PhD in relevant fields.
• A Bachelor’s, Master’s, or PhD in CS/ML or related field.
• Strong programming skills in Scala, Python, Java, C++, or equivalent languages, and data engineering skills.
• Strong understanding of machine learning best practices (e.g., training/serving skew minimization, A/B testing, feature engineering, feature/model selection), algorithms (e.g., neural networks/deep learning, gradient boosted trees, optimization), and domains (e.g., natural language processing, computer vision, personalization and recommendation, anomaly detection).
• Experience with two or more of these technologies: TensorFlow, PyTorch, Kubernetes, Spark, Airflow (or equivalent), Kafka (or equivalent), data warehouses (e.g., Hive).
• Industry experience building end-to-end machine learning infrastructure and/or building and productionizing machine learning models.
• Exposure to architectural patterns of large, high-scale software applications (e.g., well-designed APIs, high volume data pipelines, efficient algorithms, models).
• Experience with test-driven development, familiarity with A/B testing, incremental delivery, and deployment.
• Experience with the Trust and Risk domain is a plus.

Your Location:

This position is US - Remote Eligible. The role may include occasional work at an Airbnb office or attendance at offsites, as agreed to with your manager. While the position is Remote Eligible, you must live in a state where Airbnb, Inc. has a registered entity. Click here for the up-to-date list of excluded states. This list is continuously evolving