INTERNSHIP: Data Science (Python & ML)
hace 3 días
Barcelona
We’re hiring a Python‑first, statistics‑strong Data Science Intern (or junior ML Engineer) to partner with our Data Analysts on the hardest problems we have: probabilistic LTV, churn prediction, and forecasting that actually moves CAC, payback, and ROAS. ⚠️ READ THIS FIRST — Apply only if you meet this: Otherwise, feel free to check out our other junior roles on the Carrots Lab LinkedIn page › Jobs where a "convenio" isn’t required. ⭐ WHAT YOU’LL OWN (Your Mission) • LTV Prediction & Probabilistic Forecasts, • Build, compare, and iterate LTV models (e.g., survival/retention‑based, zero‑inflated + Gamma, GBMs). Produce calibrated predictions we can trust for UA and pricing., • Churn & Retention Modeling, • Predict churn windows and retention curves by app/geo/cohort to inform payback and creative/keyword strategy., • Signal Engineering for UA, • Translate model outputs into conversion signals (e.g., value‑based bidding targets) that improve Google/Meta optimization., • Revenue & Cohort Analytics (Python), • Pull, transform, and join event & purchase data (RevenueCat, AppsFlyer, Firebase, BigQuery) into model‑ready datasets., • Decision Science, • Evaluate A/B tests (frequentist or Bayesian), pricing experiments, and funnel changes with confidence intervals and practical uplift. 📈 WHAT SUCCESS LOOKS LIKE (90 Days) • LTV v1 shipped per flagship app with baseline vs. model comparison (e.g., MAE/RMSE or calibration plots) and a documented retrain cadence., • Churn or retention model v1 that beats naive benchmarks (e.g., 30‑day retention mean) and informs UA payback assumptions., • Signal spec delivered: which in‑app events/values we should pass to ad platforms, how to weight them, expected CPA impact., • Reproducible codebase: clean notebooks/scripts with README, functions, and basic tests; data pulls automated in Python., • Live dashboards (with Sergi): LTV/payback & cohort views wired to Looker for weekly decision‑making. 🧠 WHAT YOU’LL DO (Day‑to‑day) • Write Python every day: data prep, feature engineering, modeling, evaluation, and reporting visuals., • Query data from BigQuery/RevenueCat/AppsFlyer/Firebase via Python; assemble tidy training datasets., • Train and compare models (e.g., linear/GLM, XGBoost/LightGBM/CatBoost, survival analysis, time‑series)., • Calibrate predictions (Platt/Isotonic), monitor drift, and set up retraining logic., • Package insights for UA and Product: concise memos, charts, and clear “so‑what” recommendations., • Pair with Sergi (analytics & viz) and the CEO (UA/product strategy); own the technical depth. 🛠️ WHAT YOU MUST HAVE (Hard Requirements) Non‑negotiable. Please apply only if you meet all. • Python: strong hands‑on with pandas, NumPy, scikit‑learn, Jupyter., • Statistics & ML: probability, hypothesis testing, regression, classification, evaluation & calibration., • Project evidence: at least one end‑to‑end model you can show (repo/notebook; academic is fine if applied)., • Autonomy & speed: ability to self‑direct, research, and ship working code without step‑by‑step guidance., • Communication: explain complex modeling choices in plain language, with actionable conclusions., • Availability: full‑time in Barcelona (hybrid), 6+ months commitment., • Work authorization: able to work in Spain (student internship agreement or junior contract). 🎯 NICE‑TO‑HAVE (Great to see) • Bayesian modeling (PyMC/Stan), survival analysis (lifelines), time‑series (statsmodels)., • Gradient boosting (XGBoost/LightGBM/CatBoost) and model calibration., • Experience with BigQuery (via Python), RevenueCat, AppsFlyer, Firebase, Amplitude., • Basic Git, packaging, and testing discipline., • Prior exposure to subscription datasets (trials, renewals, cancellations, grace periods). 🧩 HOW WE WORK • Stack: Python, BigQuery, Looker, RevenueCat, Firebase, AppsFlyer, Amplitude, Google Cloud., • Cadence: weekly experiment reviews; model metrics > opinions; minimal meetings; fast iterations., • Culture: high speed, high standards, zero drama. We spend every euro like it’s our own. 🎁 WHAT WE OFFER (Compensation & Benefits) We offer a high-impact, high-autonomy role with a reward structure aligned to the company's growth in Barcelona. • Paid Internship: This is a remunerated full-time position designed to give you real ownership and impact — not just “student tasks.”, • The compensation is competitive for top data students or recent graduates in Barcelona., • Flexibility & Time Off: Flexible working hours, 25 days annual leave, and 1 month of 'work from anywhere' outside of Spain., • Executive Workspace & Tech: Private offices at Norrsken House Barcelona (with complimentary membership) and a generous €5,000 EUR budget for professional home-office equipment., • Wellness: Option to require a high-end Gym Membership at innerflow.es, including Spa Access in the same office building., • Cantina: Delicious, healthy, and flexible in-office catering — meals starting at just €2–€3., • Training: Dedicated Budget for an education program., • Career Trajectory: A Tailored career plan with performance reviews and salary calibrations every 6 months. If you made it all the way down here… Stop looking for entry-level jobs where they’ll spend six months “onboarding” you to clean up spreadsheets. Come here and build real things from day one. Worst case? You’ll leave smarter. Carrots Lab is an equal opportunity employer that celebrates diversity. All applicants will be considered regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, disability, gender identity, or expression.