Senior Machine Learning Engineer: ML Recall - Constructor

About Us

Launched in 2019, 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.

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.

About the Role

Your primary focus will be search retrieval and visual solutions:

• 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: Our team owns a wide range of deep learning models, and other teams build on top of them.

What Makes This Interesting

• Multi-domain, multi-language, at scale: 40+ languages, 20+ domains. The models need to generalize across all of them — without per-customer rules or overrides.
• Real room for R&D: You will experiment with new architectures and approaches, A/B test them on live traffic, and deliver measurable business value.
• The measurement challenge: You can't measure what was not returned — a missed product leaves no trace in the logs, and the query looks like it worked. Building the ground truth to catch that is part of the modeling work.

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 expertise, with 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

Benefits

• 🏝️ Unlimited vacation time: We strongly encourage all employees to take at least 3 weeks per year
• 🌎 Fully remote team: Choose where you live
• 🛋️ Work from home stipend: Resources to set up your ideal home office
• 💻 Apple hardware: Laptops provided for new employees
• 🧑‍🎓 Learning budget: Annual training and development budget for every employee
• 👪 Parental leave: Maternity & paternity leave for qualified employees
• 📈 Equity: Stock options offered in addition to base salary
• 🎉 Team offsites: Regular gatherings to connect and collaborate