Спроси Хайрика про вакансию
Сверит с твоим резюме, подскажет вилку и вопросы на собесе.
We're looking for a Staff Data Scientist to lead the technical direction, scaling, and evolution of our core AI capabilities across two tightly connected domains:
- Search, Ranking & Recommendations: advancing our multi-stage retrieval and ranking systems (Two-Tower networks, Vector Search/ANN, LTR) to optimize catalog discovery for raw physical products and designs, with a particular focus on multimodal and sequence embeddings.
- Generative AI & Visual ML: scaling our image intelligence pipeline by combining multimodal generative models with classical and deep computer vision. You'll drive systems that generate rich features and embeddings for recommendation engines, as well as tools that help merchants with content creation, smart product delayering, and automated visual asset processing.
You'll lead the modeling strategy and collaborate across our data science and machine learning engineering teams, advancing our production systems from early successes to enterprise-grade AI infrastructure.
Your daily tasks will include:
Leading & scaling recommendation and search systems
- Lead the architectural direction for candidate retrieval, multi-objective ranking, and learning-to-rank (LTR) models across raw product and design recommendations.
- Advance our personalization engines, incorporating sequence embeddings of merchant history, niche trends, and sales performance signals to surface the best products and designs.
- Connect downstream merchant sales and conversion data back into upstream design generation and candidate ranking models to continuously improve recommendation relevancy.
Driving AI design generation & vision pipelines
- Oversee image generation pipelines that combine LLMs/multimodal models with deep learning architectures (e.g., diffusion models, UNets, Vision Transformers) to generate high-converting designs for merchants.
- Deepen our classical computer vision capabilities (OpenCV) alongside deep learning vision models (e.g., ResNet, CNNs, YOLO/segmentation networks) for delayering, automated background separation, print-area quality analysis, and asset validation.
Driving end-to-end product innovation (maker focus)
- Act as a product engineer with full technical autonomy across the stack — from foundational model selection (fine-tuning, prompt engineering, self-hosting) to serving pipelines and frontend workflows.
- Rapidly prototype, iterate, and ship complete agentic pipelines and ML features using AI-assisted development (Gemini for ideation and research; Claude Code and Claude Cowork for rapid implementation).
Technical leadership, governance & mentorship
- Define and refine online/offline evaluation frameworks (NDCG, MRR, visual quality metrics, merchant conversion uplift) and oversee our continuous A/B testing strategy.
- Guide strategic make-vs-buy decisions, API vs. self-hosted fine-tuning trade-offs (e.g., open vision models, LLMs/multimodal models), and inference optimization.
- Set standards for applied ML across the organization, mentor senior ICs, run design reviews, and foster a culture of shipping measurable business impact.
