Develop and optimize CNN-based and transformer-based vision models for photo analysis and scoring

Design and prototype custom transformer architectures tailored to product creation needs

Build scalable pipelines for processing large volumes of image data and generating structured metadata

Integrate image intelligence with downstream applications such as search, ranking, and personalization

Develop and deploy transformer-based ML models for personalized product recommendations

Lead experimentation frameworks including A/B testing to improve recommendation relevance and conversion

Operate and document the full ML model development and deployment stack

Collaborate across teams to drive cross-functional technical initiatives from ideation to delivery

Ensure best practices in data management, model evaluation, explainability, and observability

Experience in software engineering with at least 3+ years in AI/ML-focused roles

Deep knowledge of computer vision techniques including CNNs, vision transformers, facial recognition, object detection, image classification, and image embedding

Strong experience with recommendation systems, collaborative filtering, deep learning for personalization, and transformer-based recommendation models

Proficiency in Python and relevant ML libraries such as PyTorch and TensorFlow

Experience deploying ML models at scale using Docker, AWS, GCP, or similar platforms

Proven ability to lead cross-functional technical initiatives from ideation to delivery

Strong grasp of ML lifecycle best practices including data management, model evaluation, explainability, and observability

Master’s degree in Computer Science or related field, preferably with a math or physics background

English proficiency at B2 level or higher

Hands-on experience with diffusion models

Experience with graph neural networks (GNNs)

Familiarity with reinforcement learning