Senior Data Scientist, Growth Alliance

The Communications tribe, a key part of the Growth Alliance, enables our brands to deliver highly personalized, meaningful interactions with our users across global markets. As a Senior Data Scientist within this team, you will drive a direct business impact by shaping the intelligence behind how, when, and what we communicate with our customers.

Your work will primarily focus on three core initiatives:

• Send Decisioning: Designing and scaling AI agents, specifically using contextual bandits, to optimize our communication channels (email, SMS, and push notifications). Your models will automate the logic that determines the most relevant message and timing for each individual user.
• Intelligent Funnel: Supporting a collaborative, cross-tribe initiative aimed at personalizing the post-click experience. You will leverage contextual bandits to match user ad-context and pre-questionnaire preferences with the optimal landing page journey.
• AI-Assisted Content & Search: Building intelligent systems to index and search internal marketing assets (images and copy). Additionally, you will develop tools that assist marketing teams in the automated composition of new, high-performing communication assets.

To succeed in this project, you should be a pragmatic and curious problem solver who excels in a cross-functional environment. Success involves translating complex user behavior into scalable models, identifying opportunities to improve our data foundations, and balancing technical depth with a strong focus on driving user engagement.

At HelloTech, flexibility and cross-functional collaboration are core to how we work. While this role is aligned to a specific Alliance, strong candidates may also be considered for opportunities across different teams or projects.

• Build, own, and iterate on RL and ML models that run in production behind high-traffic, performance-critical conversion and communication flows.
• Develop the decisioning logic that determines the best next action for each user across the funnel and the messaging lifecycle.
• Drive the architectural evolution of our contextual-bandit systems — from online exploration (Bootstrapped Thompson Sampling) toward offline policy evaluation and deterministic, low-latency inference (Counterfactual Risk Minimization, Offset Trees, model distillation).
• Partner with Engineering on system design so models integrate cleanly into the funnel and messaging architecture — including where models decide, how decisions are served at latency, and how failures are handled and rolled back.
• Own experimentation design for decisioning models: define success metrics and guardrails, and interpret results in high-noise, high-traffic environments using rigorous methods (sequential testing / SPRT, propensity handling, allocation-bias-free setups).
• Keep models safe and effective in production — monitoring performance, input-data reliability, drift, and latency, and iterating quickly when issues surface.
• Collaborate with CRM Ops agent leads, Marketing Analytics, and platform partners to turn model behaviuor into decisions marketers trust.

What you’ll bring: The Ingredients

• 5+ years of professional experience in data science, ML, or a related quantitative field, with a track record of shipping models to production.
• Proficient in Python and experienced operating in a modern ML stack (e.g. Databricks/Spark, MLflow) in close collaboration with engineers.
• Strong foundation in machine learning for personalization, plus direct experience with reinforcement learning and/or contextual bandits (e.g. Thompson Sampling, epsilon-greedy, reward design).
• Solid grounding in experimentation and causal inference — designing and analyzing controlled experiments in high-traffic settings, and reasoning about guardrails, exposure, and bias.
• Hands-on with classical ML techniques (regression, classification, clustering, recommendation systems) and comfort choosing the right tool for the problem.
• Experience with customer-behaviour data, segmentation, and production feature pipelines.
• Clear, structured communication and a genuinely collaborative, cross-functional mindset.

Nice to have:

• Off-policy evaluation/counterfactual learning, propensity methods, or sequential testing (SPRT).
• Experience with experimentation platforms (e.g. Statsig) and streaming/low-latency inference.
• Working with unstructured data as model features (embeddings, text signals).
• Exposure to marketing/CRM decisioning, deliverability, or funnel/conversion optimisation.

Above all, we are looking for individuals who will make HelloFresh better. We believe there are many different ways of developing skills and we love diverse experiences! So even if you don’t “tick all the boxes” but think you’d thrive in this role, we would really like to learn more about you.