Data Scientist

This is a fully remote position, open to applicants in Romania.

📋 Description

• Develop and construct predictive models from the ground up, beginning with:

• Churn prediction — pinpoint clients who may reduce their activity or withdraw their assets, allowing the sales team to intervene proactively.

• Upsell / cross-sell propensity — evaluate clients based on their likelihood to increase their assets under custody and identify optimal opportunities.

• Client Lifetime Value (CLV) — forecast future client value to inform resource distribution and prioritize relationship management.

• Manage the complete modeling lifecycle:

• Collaborate with raw trading, transactional, and behavioral data sourced from our data warehouse.

• Define target variables and translate business concepts (e.g., what "churn" means in a brokerage context) into measurable ML objectives.

• Create features from client activities, trading behaviors, market conditions, and engagement indicators.

• Select, train, validate, and refine models — starting with simple approaches and increasing complexity where justified.

• Establish monitoring systems for model performance, data drift, and degradation over time.

• Provide daily client-level scores that are integrated into CRM workflows and sales activities.

• Connect data science with business objectives:

• Convert model results into actionable insights for non-technical sales managers.

• Collaborate with sales leadership to formulate interventions based on model predictions.

• Present findings, assumptions, limitations, and recommendations to senior stakeholders.

⛳️ Requirements

• 4+ years of practical experience in building and deploying predictive models addressing real business challenges (classification, regression, scoring).

• Proficient in Python (pandas, scikit-learn, XGBoost/LightGBM/CatBoost) and SQL.

• Proven ability to independently frame ambiguous business issues as ML tasks — define targets, engineer features, and select methodologies.

• Experience with large-scale tabular data: feature engineering, managing class imbalance, temporal validation, and preventing data leakage.

• Capable of communicating model outcomes to non-technical stakeholders in clear, actionable terms.

• Background in working with time-series or event-based behavioral data.

• Strong advantages include:

• Experience with churn prediction, propensity modeling, CLV, or customer scoring across any industry.

• Familiarity with survival analysis (Cox proportional hazards, time-to-event modeling).

• Experience in model monitoring in production: detecting data drift, retraining pipelines, and implementing champion-challenger frameworks.

• A background in financial services, brokerage, or fintech.

• Experience with probabilistic models for CLV (BG/NBD, Pareto/NBD, Gamma-Gamma).

• Knowledge of SHAP, LIME, or similar model interpretability techniques.

• Familiarity with data warehousing tools (BigQuery, Databricks, or equivalent).

🏝️ Benefits

• Competitive salary that reflects your expertise and the value you contribute.

• Flexibility to suit your lifestyle — work from home, at our office, or a combination of both. You choose what works best for you.

• A customizable benefits package — select the options that fit your life, rather than a generic bundle.

• A truly enjoyable workplace — a casual, collaborative culture where your ideas are valued and bureaucracy is minimal.

• Opportunities for continuous learning — ongoing training, educational programs, and support to enhance your expertise in a rapidly evolving industry.

• Opportunities for connection beyond your desk — events that foster team networking and celebration.

• Global exposure — collaborate with talented colleagues from around the world within a business serving clients in over 100 countries.