Applied AI/ML Scientist, Intern

About the job

Responsibilities

• Predict how an order will be packed by building models that learn from item characteristics and combinations.
• Recommend better packing methods by developing models that understand items from images and text to reduce shipping costs and improve efficiency.
• Understand products from a catalog by training multimodal deep learning models to infer physical characteristics from images, text, and other signals.
• Survey the literature and existing approaches to identify promising ideas.
• Prototype and train models offline, benchmarking against current methods.
• Build out the strongest approach into a working implementation.
• Work with Applied Scientists and ML Engineers to test implementations against live traffic.
• Present findings and recommendations to the team.

Requirements

• Currently enrolled in or recently graduated from a Master's or PhD program in Computer Science, Machine Learning, Statistics, Electrical Engineering, or a related technical field.
• Hands-on experience building deep learning models (e.g., PyTorch), ideally with images, text, or both, including fine-tuning pre-trained models or working with embeddings.
• Familiarity with gradient-boosted trees and other tabular ML methods.
• Strong Python and SQL skills.
• Ability to read research papers and translate promising ideas into working code.
• Solid grounding in statistics and model evaluation, including benchmarking and estimating uncertainty.
• Comfort working with noisy or incomplete real-world data.
• Enthusiasm for tackling ambiguous problems and learning new tools and techniques.

Benefits

• Paid internship
• Flexible start dates
• Extensions may be offered
• Competitive pay
• Equity
• Comprehensive benefits