Remote · Middle
Price is one of the marketplace's strongest levers: GMV, profitability, and how attractive it is to buy from us directly depend on it. The pricing team is building a dynamic pricing system. The system regularly recalculates recommendations for a large number of SKUs and manages discounts to grow sales without losing margin.
The scope includes demand forecasting, elasticity assessment, price and discount optimization under business constraints, and continuous A/B experiments with analysts and product managers.
Responsibilities:
- Demand and Price Models: Demand forecasting, assessing the impact of price and discounts on sales, optimal price recommendations
- Model Quality: Feature engineering, offline validation, error analysis, selection and comparison of ML approaches
- Data: Dataset and feature preparation, EDA, input data quality control
- Experiments: Designing and analyzing A/B tests with analysts, evaluating the impact on GMV, profitability, and sales
- Production and Reliability: Developing an ML system that recalculates prices for a large assortment; monitoring model behavior after launch and analyzing incidents
- Engineering Culture: Code review, architecture discussions, documentation of solutions and experiment results
Our Stack:
- ML/DS: Python, pandas/polars, NumPy, scikit-learn, CatBoost/LightGBM, PyTorch
- Data: ClickHouse, Trino, Airflow
- Production: Git, Docker, CI/CD
- A/B Experiments: GrowthBook
What we expect:
- 3+ years of commercial experience in ML/DS: trained models and brought them to production or regular use
- Proficient Python and core DS stack; experience with gradient boosting and/or PyTorch
- Proficient SQL, experience with big data
- Understanding of A/B tests: statistical significance, confidence intervals, power and MDE, correct interpretation of results
- Ability to write maintainable code: Git, Docker, basic understanding of CI/CD and pipeline orchestration
- Independence: ability to break down tasks, propose solutions, and bring chosen ones to completion
- Ability to explain model limitations and results to analysts, developers, and product managers
- Evaluate models not only by offline metrics but also by their impact on the business
Will be a plus:
- Experience with demand forecasting, price elasticity, price or discount optimization
- Understanding of causal inference: why you can't just train a "price → demand" model on historical data
- Experience in e-commerce or retail
Hiring Process:
- HR Interview (30 min): team, context, your experience and expectations
- Tech-1 (60 min): Python, SQL, ML theory
- Tech-2 (60 min): ML System Design
- Final (60 min): Interview with the hiring manager
Why this is interesting:
- We provide a wide area of responsibility and the opportunity to influence architectural and product decisions. We are also happy to discuss and implement your initiatives
- Unique culture – we have preserved the startup spirit while building mature processes
- We set measurable goals as a team and don't just achieve them "for show" but measure the effectiveness and overall impact of our work on the business
- Work in teams of strong specialists who value deep expertise and engineering thinking
- Teams listen to and hear each other, acting as partners rather than executors
What we offer:
- Remote work from anywhere in the world or a cozy office in Tashkent
- You can grow in an engineering or managerial track, and we have a regular performance evaluation system
- We pay at the level of top Russian market companies
- Training and development – we support development both within the company and externally (meetups, conferences, professional training, publications). We also help develop your personal brand
- Base – a community of professionals with a desire to do great work. A pleasant bonus – voluntary medical insurance linked to your location, training, and other perks
