About the company
Constructor is an AI-first ecommerce search and discovery platform that helps shoppers find the right products at the right time and enables leading global e-commerce brands to drive meaningful revenue and conversion gains.
About the role
As a member of the ML Recall team, you will improve the e-commerce experience for hundreds of millions of users across the world by building the retrieval layer of our search engine. The mission is to make sure the product a shopper looks for is always among the results - for any query, in any language, in a few milliseconds.
Responsibilities
- Search Recall: a modern retrieval stack with dense and sparse models, plus query understanding. Latency is a strict requirement, so quality vs speed tradeoff is constant.
- Visual and multimodal search: end-to-end visual solutions: image search, shop the look, visual recommendations.
- Models as a platform: own a wide range of deep learning models that other teams build on top of.
- Experiment with new architectures and approaches, A/B test them on live traffic, and deliver measurable business value.
- Build ground truth to catch missed products that leave no trace in the logs.
Requirements
- 4+ years shipping production ML systems
- Experience with search, information retrieval, or recommendation systems
- Hands-on experience training, fine-tuning, and evaluating transformer models
- Strong Python and PyTorch. Fluency in data orchestration tools (Spark, Airflow)
- Experience owning a model end to end - from problem framing to rollout
- Experience designing and running A/B tests to validate model impact
- Excellent English communication skills
Conditions
- Unlimited vacation time (at least 3 weeks per year encouraged)
- Fully remote team - choose where you live
- Work from home stipend
- Apple laptops provided for new employees
- Training and development budget for every employee, refreshed each year
- Maternity & Paternity leave for qualified employees
- Base salary: $80k–$120k USD, depending on knowledge, skills, experience, and interview results
- Stock options - offered in addition to the base salary
- Regular team offsites