Overview

Day30 helps subscription apps improve paid acquisition ROI by providing predictive signals to optimise ad spend. We connect directly to mobile measurement partners (MMPs) to analyse behavioural event data, build ML models that predict high-value conversions weeks in advance, and deliver these predictions to advertising platforms without compromising user privacy. We are a two-founder London startup combining deep expertise in performance marketing and machine learning. As our first data scientist, you\'ll be founder-adjacent, working directly with our CEO and CTO to transform our current ML capabilities into a scalable, automated platform that will power hundreds of clients.

This role offers rare technical autonomy: you\'ll work across the entire ML pipeline from data ingestion through production deployment, collaborate with the CTO and software engineers, and have direct input on all technical decisions. You should thrive on solving complex behavioural modelling problems and want to see your work immediately impact real business outcomes.

What You\'ll Do

• Core ML Pipeline Development: Design and implement end-to-end ML pipelines from data ingestion through model deployment and signal delivery
• Transform client-specific notebooks into modular, config-driven pipelines using orchestration tools (Prefect/Airflow)
• Build robust API connectors handling schema evolution, incremental updates, and data quality validation
• Model evaluation frameworks blending technical metrics (precision, recall, PRAUC, probability calibration) with business outcomes

• AutoML & Model Optimisation: Develop time-series AutoML capabilities and advanced feature engineering for event-based data
• Multi-model design for different prediction horizons and conversion definitions
• Hyperparameter tuning using frameworks such as Optuna, AutoGluon, or H2O

• MLOps & Platform Engineering: Establish MLOps practices (experiment tracking, model registry, monitoring)
• CI/CD & deployment collaboration with engineering
• Data quality monitoring and model drift detection
• Scalability design from a dozen customers today to 100+ within 12 months

• Technical Leadership: Partner with the CTO on technical strategy and architecture decisions
• Collaboration with client teams to understand data nuances and maximise predictive value
• Mentor juniors through code reviews and pairing as the team grows
• OKRs & technical roadmap co-created with the founding team

Requirements

The ideal candidate must have 5-8+ years building production ML systems with demonstrable business impact; strong experience with time-series analysis and behavioural event modelling; deep expertise in Python with high code quality standards; experience with modern ML stack (pandas/polars, sklearn, xgboost, PyTorch/TensorFlow); proven track record delivering end-to-end ML pipelines (ingestion → feature engineering → training → deployment → monitoring); hands-on experience with cloud data warehouses (e.g. BigQuery, Snowflake); track record of building automated, scalable systems from initial prototypes; Right to Work in the UK (visa sponsorship not available); ability to work from Central London office 3 days/week.

You may be a great fit if you have experience with AutoML frameworks (e.g. AutoGluon, TPOT, Optuna, H2O.ai); MLOps tooling (e.g. MLflow, Weights & Biases, Evidently); orchestration tools (Prefect, Airflow, Dagster); building robust API/ETL connectors; statistical depth beyond standard metrics (calibration, cost-sensitive learning, causal inference); and enthusiasm for leveraging the latest LLM tooling for accelerated AI-enabled delivery without sacrificing quality.

Domain Knowledge Bonus Points (beneficial but not required): marketing attribution and conversion modelling; mobile app analytics and user lifecycle prediction; ad-tech ecosystem and privacy regulations (ATT, GDPR); subscription business metrics and retention modelling.

Benefits

• Base Salary: Up to £95,000 per annum (depending on experience)
• Equity: Meaningful options as first technical hire
• Holidays: 25 days of annual paid leave, plus bank holidays
• Flexibility: 3 days/week in Central London office, remote otherwise
• Equipment: Top-spec MacBook Pro and any tools you need
• Learning Budget: Conferences, courses, and resources to stay current