Senior Applied Data Scientist — Marketing Mix Modeling

Opella is a global consumer healthcare company headquartered in Paris, France, and one of the world's largest players in the OTC and self-care market. With around 11,000 employees, 13 manufacturing sites, and over 100 trusted brands — including Allegra, Doliprane, and Enterogermina — the company delivers science-based health solutions to consumers worldwide. Following its 2025 transition to a standalone business, Opella continues to expand its leadership in self-care, driven by innovation, digitalization, and responsible growth.

About the Team

The Advertising & Promotion (A&P;) Analytics team builds the data science and decision-support systems that guide how Opella invests its general marketing budget across brands, channels, and markets. We combine predictive and causal modeling , scenario analysis , and mathematical optimization to turn measurement into action — helping marketing, finance, and brand stakeholders evaluate trade-offs and commit to multi-million-euro investment decisions. Our work spans the full lifecycle: from modeling, through scenario and what-if engines, to production APIs and stakeholder-facing tools.

Who You Are

You are a senior data scientist who thrives at the intersection of modeling, optimization, and product thinking , comfortable owning complex problems end-to-end — from framing the business question, to choosing the right modeling approach, to shipping a robust system that stakeholders actually use. You partner closely with engineers, product, and business stakeholders, moving comfortably between deep technical work and stakeholder conversations — translating modeling choices into business trade-offs, and business questions into well-scoped problems. You enjoy challenging the status quo to make sure Opella's AI solutions are scientifically sound, operationally reliable, and impactful for the patients and consumers of tomorrow.

Job Highlights

- Own problems end-to-end : from framing and modeling, through experimentation and productionization, to monitoring and adoption.

- Design and build decision systems combining predictive/causal modeling, scenario analysis, and optimization — including planning and what-if tools that let stakeholders evaluate trade-offs across channels, brands, markets, and constraints.

- Productionize modeling and optimization engines and APIs with a focus on robustness, performance, and interpretability.

- Apply expertise in machine learning, statistics, time-series forecasting, optimization, and Generative AI ,



and use data analysis, visualization, and storytelling to scope, define, and deliver AI-based data products.

- Contribute to the team's technical direction through code review, design discussions, and knowledge sharing , partnering closely with product, engineering, MLOps, and business stakeholders.

- Invest in long-term code health : refactor where foundations need strengthening, pay down technical debt, and prefer maintainable, well-tested solutions over short-term workarounds.

Key Functional Requirements & Qualifications

- Hands-on AI/ML modeling experience with complex datasets, with strong theoretical grounding in most of: supervised/unsupervised learning, Bayesian statistics, mathematical optimization (LP/MILP, heuristics), simulation and what-if analysis .

- Demonstrated experience designing and shipping decision-support systems end-to-end (not just notebooks) — production code, APIs, monitoring, and stakeholder adoption — in agile, product-focused environments.

- Experience delivering data science projects in commercial, operational, or planning domains — for example marketing analytics, forecasting, recommender systems, supply/manufacturing, or pricing — is a strong plus.

- Comfortable in cloud and high-performance computing environments (AWS preferred; also Databricks, Azure).

- Excellent written and verbal communication, business analysis, and data storytelling — able to translate technical work for business audiences — and a demonstrated ability to collaborate effectively in cross-functional teams (data scientists, engineers, MLOps, product, business).

- Previous experience in business areas such as Marketing, Finance, Manufacturing & Supply, or Operations .

- Nice to have: experience in life sciences, healthcare, or CPG , and in a complex global organization.

Key Technical Requirements & Qualifications

Education

- PhD in a quantitative discipline (mathematics, computer science, operations research, engineering, physics, statistics, economics, or similar) with strong coding skills, OR Master's in a relevant domain with 4+ years of analytical / applied data science experience.

Optimization & Operations Research





- Familiarity with mathematical optimization concepts and tooling (e.g. Pyomo, OR-Tools, Gurobi , or similar). Hands-on experience shipping optimization-based decision systems is a plus.

Statistics & Causal Inference

- Solid grounding in statistical modeling and inference . Exposure to causal inference (e.g. Bayesian methods or quasi-experimental approaches) is a plus.

Programming & Software Engineering

- Expertise in Python (Scala, Kotlin, or Java a plus), with strong OOP, design patterns, modular architecture, coding standards, version control, testing, and software engineering best practices .

- Strong commitment to maintainable, sustainable code : comfortable refactoring legacy components, raising the engineering bar through reviews, and choosing solutions that age well over short-term fixes that create future pain.

- Experience building production-ready APIs and services (e.g. FastAPI), and familiarity with SQL and modern data tooling (Pandas/Polars, Spark).

CI/CD

- Proficiency in CI/CD pipelines for ML models, optimization services, and data pipelines (e.g. GitHub Actions, GitLab CI/CD ), with version control applied to code, data, and model artifacts.

MLOps

- Experience operationalizing ML and decisioning systems with automated workflows for training, evaluation, deployment, and monitoring — hands-on with MLflow for experiment tracking, model registry, and lifecycle management.

- Knowledge of infrastructure for deploying and scaling models (cloud, containers, Kubernetes); effective collaboration with DevOps and platform teams.

Data Visualization & APIs

- Knowledge of tools such as Plotly, Streamlit , or similar — and an opinion on what makes a good stakeholder-facing tool.

- Experience designing and consuming enterprise-level APIs .

Generative AI (nice to have)

- Exposure to RAG workflows, agentic frameworks, vector databases, prompt engineering, and LLMs , with interest in applying them to analytics and decisioning use cases.

Other Skills & Competencies

- Strong English communication; Spanish and/or French are a plus.

- Analytical, engineering-oriented mindset with focus on quality, reliability, and reproducibility.

- Effective in remote, distributed, and multicultural team environments.

- Able to balance technical excellence with business deadlines ; proactive, goal-driven, and generous with knowledge.

- Passion for innovation and emerging standards (e.g. MCP, agentic frameworks, modern optimization tooling ).

📌 Senior Data & AI Scientist (Colombia)
🏢 Opella Healthcare Group
📍 Colombia