Data Scientist

Overview

About SureBright
SureBright is a trailblazing start-up, redefining how warranties and insurance are distributed in the digital age. Think AppleCare for everything — we're building the platform that enables premium protection plans for any product sold online. Our cutting-edge platform serves retailers and tech companies across the US and Canada. Backed by world-class investors including Y Combinator, we’re pioneering technology that powers next-gen warranty and insurance distribution.

Why Join Us?
We’re assembling a core team of product-first, data-driven innovators to help shape the future of embedded warranties. As a Data Scientist at SureBright, you’ll take ownership of building data-driven systems that power intelligent product categorization, feature extraction, claim prediction, and personalized recommendations. This is your opportunity to work with rich, industry-first datasets, develop machine learning models from scratch, and directly influence the customer journey for millions of online shoppers.

🛠️ What You’ll Do

Build, train, and deploy ML models for automated product categorization across diverse e-commerce catalogs.

Develop product feature extraction pipelines to identify attributes like brand, dimensions, materials, and warranty eligibility from text, images, and structured data.

Design predictive models for warranty claim likelihood, fraud detection, and optimal pricing strategies.

Implement scalable data pipelines and ETL workflows for high-volume product and transaction data.

Build recommendation systems to suggest warranty plans based on product type, features, and customer profile.

Collaborate with engineering to integrate ML models into production systems, ensuring performance and scalability.

Conduct exploratory data analysis to uncover insights that shape product strategy.

Define, track, and optimize business KPIs with automated dashboards and real-time reporting.

Research and apply cutting-edge techniques in NLP, computer vision, and GenAI for e-commerce use cases.

🔍 What We’re Looking For

2–4 years of experience in data science, machine learning, or applied AI (start-up or e-commerce experience a plus).

Strong skills in Python (pandas, NumPy, scikit-learn, PyTorch/TensorFlow) and SQL.

Experience with NLP for text classification, entity extraction, or topic modeling.

Knowledge of computer vision techniques for image classification or object detection.

Familiarity with product taxonomy creation and ontology design.

Experience working with large, messy, real-world datasets and building production-ready ML solutions.

Excellent communication skills — able to distill complex analysis into clear, actionable insights.

A bias for action, ownership, and delivering impact in a fast-paced environment.

💡 Bonus Points For

Prior experience in product catalog management or retail data.

Exposure to AWS ML ecosystem (SageMaker, Comprehend, Rekognition).

Experience with event-driven or streaming data systems (Kafka, Kinesis).

Familiarity with vector databases (Pinecone, Weaviate) for semantic search.

Hands-on experience with GenAI for classification, summarization, or image tagging.

🌟 Perks & Benefits

Join a VC-backed YC startup from the ground floor.

Collaborate with a world-class, high-performance team.

Build ML systems that directly shape the e-commerce warranty experience.

Opportunity to work on pioneering GenAI and multi-modal AI applications.