[8BE] Senior Data Scientist, Probabilistic Modeling (Architecture, Adjacent)

We're seeking a Senior Data Scientist with deep expertise in probabilistic AI and statistical machine learning to support a client's e-commerce platform. In this role, you'll design and validate probabilistic models — covering dynamic pricing, shipping cost estimation, recommendations, and segmentation — while working closely with our solution architect, the client's CTO, and the client's engineering team to shape how those models fit into the platform's architecture.

Project Length: 3 - 6 months.

Key Responsibilities

• Bayesian modeling and inference: Design and implement Bayesian statistical models — priors, likelihoods, and posterior inference — to support decisioning under uncertainty across pricing, segmentation, and demand-related use cases.
• Markov chains and Hidden Markov Models: Build Markov chain and Hidden Markov Model formulations for sequential and behavioral patterns (e.g., customer lifecycle stages, state transitions), producing outputs that downstream services can consume.
• MCMC and Metropolis-Hastings sampling: Apply Markov Chain Monte Carlo methods, including Metropolis-Hastings sampling, to estimate posterior distributions for models without closed-form solutions, and validate convergence and sampling quality.
• Mixture modeling: Develop mixture models — Gaussian Mixture Models in particular — to support segmentation use cases, identifying latent customer or product groupings from transactional and behavioral data.
• Expectation-Maximization: Implement Expectation-Maximization for latent-variable estimation underlying mixture models and related unsupervised learning tasks.
• Architecture collaboration: Work alongside our solution architect and the client's CTO to align model design with platform architecture. While this is not an architecture-ownership role, you should be able to reason about integration points, service boundaries, and technical tradeoffs well enough to operate with a reasonable degree of autonomy and reduce the support load on the architect.
• Production translation: Guide backend engineering on how statistical models translate into production service architecture — informing API design, data contracts, and integration points within the platform's existing microservices and event-driven pipelines.
• Model lifecycle management: Define the approach for model training, validation, versioning, monitoring/drift detection, and retraining cadence once models are in production.
• Roadmap collaboration: Partner with delivery and engineering leads to size, sequence, and estimate probabilistic/statistical modeling initiatives on the product roadmap.
• Documentation and handoff: Document modeling assumptions, methodology, and validation results, and provide clear hand-off guidance so models remain maintainable by the engineering team after the engagement.

• 90% English written and oral (at least B2 level) with excellent communication skills.
• Senior-level experience, with the ability to communicate confidently with both technical and business stakeholders, should be comfortable discussing business impact and tradeoffs directly with CTO.
• Strong, demonstrable background in designing Bayesian statistical models, Markov chains, Hidden Markov Models, MCMC methods (including Metropolis-Hastings sampling), mixture models (ideally Gaussian Mixture Models), and Expectation-Maximization — classical predictive modeling, not standard modern supervised/LLM-based ML.
• Experience designing statistical/ML models with production deployment in mind is strongly preferred; hands-on production implementation is a plus but not mandatory — the priority is the ability to architect the modeling approach and guide engineering through it.
• Proficiency in Python (or R) with standard probabilistic/statistical libraries (e.g., PyMC, Stan, scikit-learn, NumPy/SciPy) for model development and validation.
• Ability to reason about how statistical/mathematical models translate into service-oriented production architecture — understanding of APIs, data contracts, and how to work directly with backend engineers and architects to integrate models.
• Solid understanding of version control, testing practices, and CI/CD, sufficient to collaborate effectively with an engineering team on production delivery.
• Strong written and verbal communication skills, with the ability to explain model behavior, assumptions, and uncertainty to non-technical stakeholders.

Preferred Qualifications/Nice to have

• Experience in e-commerce or retail domains, particularly pricing optimization, customer segmentation, or demand forecasting.
• Familiarity with how ML models integrate into microservices architectures (REST/GraphQL) and event-driven systems (e.g., message queues/pub-sub) hands-on deployment experience is a plus but not expected.
• Familiarity with common backend service ecosystems (e.g., .NET, Java, or Node.js) even if modeling itself is done in Python — for a smoother handoff to the production engineering team.
• Exposure to MLOps concepts such as model registries, monitoring, or feature stores — helpful for handoff conversations, but not a core requirement.
• Background in pricing science, recommendation systems, or marketing analytics.
• Experience communicating modeling recommendations directly to business or executive stakeholders (e.g., CEO/CTO-level conversations).

We are accepting applications from LATAM countries