Senior Data Scientist (Maternity cover)

Location: Ireland, Dublin (IE)

Description

We are looking for a Senior Data Scientist to join our classification team. A critical component to enabling cross-border is delivering seamless clearance through customs. This is also an incredibly challenging problem where Global-e has radically changed the industry by delivering the world's first machine learning-based, highly accurate classification system that replaces the need for people to inspect and classify individual products. This capability enables our clients to ship goods from anywhere in the world to anywhere in the world directly from their stores and fulfillment centers, keeping customers happy with fast and seamless delivery. 

Main Responsibilities: 

• Research, design, maintain, and evolve the company's machine learning models to support the world’s fastest and most accurate classification and restriction systems for cross-border trade. 
• Develop, fine-tune, and deploy Large Language Models (LLMs) to enhance classification accuracy and automation capabilities. 
• Engage in both exploratory data analysis to identify trends and formulate modeling approaches to solve problems
• Use model outputs to deliver both short-term commercial impact and longer-term business value and customer experience
• Partner closely with product, engineering and other business leaders by providing consulting and analytic services that help influence product decisions with data
• Document clear insights and analysis for stakeholders to understand and take actions accordingly
• Continuously evaluate model performance and drive iterative improvements to enhance accuracy and effectiveness
• Help cultivate a culture of experimentation through sharing of best practices and trainings

Requirements

• At least 5 years of experience in data science, solving real-world problems, and using modern technologies to develop ML models. 
• Experience with the full lifecycle of a data product - ideation to productionizing and iterating. 
• Experience with training, fine-tuning, and deploying LLMs, as well as applying state-of-the-art architectures to domain-specific challenges. 
• Experience with NLP algorithms and approaches and their applications to taxonomies, recommendations, and search domains. 
• Solid programming skills to code, build, and test models. 
• Knowledge of and appetite for mathematical principles that are the foundation of ML methods. 
• Familiarity with transformer-based architectures (e.g., BERT, GPT) and their application to classification and predictive modeling. 
• Experience in optimizing and scaling deep learning models for real-world deployment in production environments. 
• Strong data visualisation skills
• Excellent communication skills, both written and verbal; the ability to convey your message to team members and other stakeholders