Senior Data Scientist, Computer Vision

Summary

Join Airbnb's AirCover Data Science team as a Computer Vision expert to build scalable systems for detecting and resolving trip issues. You will leverage large-scale unstructured data, incorporate multimodal signals for fraud detection, determine fair payment values, automate workflows, and optimize product presentation. A typical day involves identifying business opportunities, collaborating with cross-functional teams, developing and deploying machine learning models, presenting work internally, and publishing externally. This US-remote eligible position requires 5+ years of experience and a Master's or PhD in a relevant field. The role offers a competitive salary, bonus, equity, benefits, and Employee Travel Credits.

Requirements

• 5+ years of relevant industry experience (e.g. ML scientist, tech lead, junior faculty) and a Master’s degree or PhD in relevant fields
• Expertise in Deep Learning and its framework (PyTorch preferred) and Transformers architectures
• Hands-on ‘builder’ experience with Compute Vision and Multimodality problems
• Strong fluency in Python and SQL
• Deep understanding of Machine Learning lifecycle best practices (eg. training/serving, feature engineering, feature/model selection, labeling, A/B test), algorithms (eg. gradient boosted trees, neural networks/deep learning, optimization) and domains (eg. natural language processing, computer vision, personalization and recommendation)
• Proven ability to communicate clearly and effectively to audiences of varying technical levels, observation causal inference skill is a plus
• Ability to take a product-oriented mindset in using conceptual and innovative thinking to develop and apply solutions taking into consideration the user experience

Responsibilities

• Leverage large scale unstructured data using computer vision and document understanding techniques to gauge the quality, relevance and authenticity of evidence submitted for issues during trip
• Incorporate multimodal signals to develop proactive, agile, and explainable fraud detection systems through embedding and deep learning
• Determine fair value of the payment across image, receipt, and segmentation
• Automate low complexity workflow with Agentic AI approach, and augment high complexity human decision with intelligent signals from above
• Optimize presentation of AirCover products through designing thoughtful personalization
• Identify high-impact business opportunities through data exploration and model prototype, translate business problem into scientific formulations
• Work collaboratively with cross functional partners including software engineers, product managers, operations and research, to refine requirements for machine learning models, drive scientific decisions, and quantify impact
• Hands-on develop, productionize, and operate machine learning models on paved path, including both batch and real-time use cases, structured and unstructured data
• Regularly present work internally at monthly meetings to technical, engineering and product stakeholders to iterate and generate excitement on roadmap progress
• Publish externally and engage with the scientific community to advance Airbnb’s standing

Preferred Qualifications

• Proven mix of strong intellectual curiosity with high level of pragmatism and engagement with the technical community. Publications or presentations in recognized journals/conferences is a plus
• Proficiency with LLMs and/or related AI, NLP, including deep learning, information retrieval, or knowledge extraction

Benefits

This role may also be eligible for bonus, equity, benefits, and Employee Travel Credits