Senior Data Scientist

Who Are We?

We are Welltech — a global company with Ukrainian roots and a powerful mission: to move everybody to start and stay well for life. Today 25.5 million users have trusted Welltech to help them build healthy habits — a testament to the real value our innovative, engaging wellness solutions deliver every day. 🌍

With five hubs across Cyprus, Ukraine, Poland, Spain and the UK and a diverse, remote-friendly team of 700+ professionals, we continue to scale rapidly. Our innovative apps — Muscle Booster, Yoga-Go and WalkFit — empower millions to transform their lifestyles and unlock their personal wellness journeys.

Welltech is where your impact becomes real. And our values clearly attest to that: we grow together, we drive results, we lead by example and we are well-makers.

If this looks like you and you thrive in a fast-paced environment, you’ll fit right in at Welltech. Let’s build wellness for millions together.

Required Skills:

• 3+ years (Mid) or 5+ years (Senior) of experience in Data Science or product analytics involving machine learning;
  

• Strong proficiency in Python and SQL;

• Hands-on experience with core DS/ML libraries such as NumPy, Pandas, Scikit-learn, XGBoost / CatBoost;
  

• Solid understanding of core ML algorithms (gradient boosting, predictive models) and evaluation metrics (classification/regression metrics, business metrics);
  

• Proven experience developing, evaluating, and maintaining ML models for real business problems, especially forecasting and predictive modeling;
  

• Practical experience building and maintaining end-to-end ML pipelines: data preparation, feature engineering, training, validation, deployment, and monitoring;
  

• Hands-on experience with AWS services (e.g., SageMaker, Glue, Redshift, S3, Lambda)
  

• Understanding of MLOps practices: model versioning, automated retraining, monitoring, basic CI/CD;
  

• Strong collaboration skills and experience working closely with Marketing, Product, and Engineering teams;
  

• Ability to translate business problems into modeling tasks and explain model results to non-technical stakeholders;
  

• Experience working with LLM APIs in applied use cases (e.g., automation, text processing, internal tools).
  

Main Responsibilities:

• Design and deploy ML models that support critical business functions such as LTV prediction, user classification, personalization, and content tagging;
  

• Analyze model performance over time, identify drift and degradation, and propose improvements;
  

• Work closely with Marketing teams to support decision-making, experiment analysis, and performance forecasting;
  

• Improve data pipelines and model deployment flows together with data engineers;
  

• Design and maintain production ML pipelines: feature preparation, training jobs, inference workflows;
  

• Evaluate alternative modeling approaches and proxies for forecasting tasks;
  

• Contribute to automation of ML workflows and internal tools that improve model usability and reliability;
  

• Support business stakeholders with analytical insights related to monetization, retention, and LTV.
  

Nice to Have:

• Experience with subscription-based products or LTV modeling;
  

• Experience with model calibration and monitoring in production;
  

• Background in Marketing Analytics (e.g., attribution, ROI analysis, uplift modeling);
  

• Experience with Docker and Airflow;
  

• Interest in model interpretability and explainability.
  

Tech Stack:
Python, SQL, DBT, AWS (SageMaker, Glue, Lambda, Redshift, Spectrum), Docker, Airflow, GitLab, Terraform, Flask, Streamlit, LLM APIs.

About Our Team:
We are the core ML team within a product-focused company. Our mission is to design and deploy impactful machine learning solutions that enhance decision-making and automate key business processes. We work closely with stakeholders across the company and take ownership of end-to-end ML systems, from raw data to deployed models and monitoring.

Our recent work includes:

• Building and calibrating LTV prediction models tailored to multiple product verticals.

• Researching the relationship between user engagement and monetization using ML tools.

• Developing a personalized exercise recommendation system and continuously optimizing it based on user feedback and behavioral data.

• Segmenting users through advanced clustering techniques to support product targeting.

• Using AI-based models to classify and analyze user reviews across multiple categories.

• Improving creative testing through model-driven insights to optimize campaign efficiency.