BACKEND ENGINEER - RANKING TEAM

About UsConstructor is the next-generation platform for search and discovery in ecommerce, built to explicitly optimize for metrics like revenue, conversion rate, and profit.
Our search engine is entirely invented in-house utilizing transformers and generative LLMs, and we use its core and personalization capabilities to power everything from search itself to recommendations to shopping agents.
Engineering is by far our largest department, and we’ve built our proprietary engine to be the best on the market, having never lost an A/B test to a competitive technology.
We’re passionate about maintaining this and work on the bleeding edge of AI to do so.
ut of necessity, our engine is built for extreme scale and powers over 1 billion queries every day across 150 languages and roughly 100 countries.
It is used by some of the biggest ecommerce companies in the world like Sephora, Under Armour, and Petco.
e’re a passionate team who love solving problems and want to make our customers’ and coworkers’ lives better.
We value empathy, openness, curiosity, continuous improvement, and are excited by metrics that matter.
We believe that empowering everyone in a company to do what they do best can lead to great things.
onstructor is a U.
.
based company that has been in the market since .
It was founded by Eli Finkelshteyn and Dan McCormick who still lead the company today.
bout the TeamThe Ranking team, within the Machine Learning chapter, plays a central role in implementing algorithms that optimize for business KPIs like revenue & conversions.
We focus on metrics over features, arming our ranking algorithms with powerful capabilities that bring value to customers in the way they care the most about.
As a member of the Ranking team, you will be surrounded by and encouraged to use world-class analytical, engineering and machine-learning techniques on big data to shape the evolution and scale of our ranking algorithms.
The team owns all stages of products ranking for Search, Browse, and Autocomplete experiences, including base ranking, second-stage ranking, and ranking explanation.
ne of the main services the Ranking team owns is the ML Ranking Service which is a high-load distributed REST service deployed in the cloud and developed in Python programming language.
The service extensively uses in-memory and NoSQL DBs (for signals and model metadata storage).
We support service deployment and stability.
We have monitoring set up with Prometheus, PagerDuty, Sentry, and custom internal APIs with FastAPI).
Challenges you will tackleA primary focus of this job is to design, deliver & maintain highload real-time web services in close collaboration with other great engineers from the Ranking team.
The job can consist of, but is not limited to.
Build, deploy, and support robust high-load machine learning-based real-time systems for search and browse experiences.
Collaborate with technical and non-technical business partners to develop and update ranking functionalities Optimize current ranking service performance to process requests faster Optimize signals delivery and retrieval (aka Feature Store) for machine learning model inference Communicate with stakeholders within and outside the team