Senior Data Scientist, Probabilistic Modeling – Architecture, Adjacent

Software Mind

. Design and validate probabilistic models for dynamic pricing, shipping cost estimation, recommendations, and segmentation .

Posted 9/24/2026full-timeRemote • RomaniaSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and validating probabilistic models, including Bayesian statistical models and Markov chains, while effectively collaborating with technical and business stakeholders. Proficient in Python or R, with a strong understanding of production deployment and backend engineering integration.

Highest-signal resume keywords

Bayesian Statistical ModelsMarkov ChainsMCMC MethodsPython or R ProficiencyE-commerce Experience

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Probabilistic ModelsHidden Markov ModelsGaussian Mixture ModelsExpectation-MaximizationStatistical LibrariesModel ValidationData ContractsVersion ControlCI/CD PracticesModel Deployment

Soft Skills

Strong Communication SkillsStakeholder Engagement

Tools & Technologies

PyMCStanScikit-learnNumPySciPyRESTGraphQL.NETJavaNode.js

Industry Keywords

Pricing OptimizationCustomer SegmentationDemand ForecastingMLOpsMarketing Analytics

Tech Stack

Tools & technologies

GraphQLJavaJavaScriptMicroservicesNode.jsNumpyPythonScikit-Learn.NET

About the role

Key responsibilities & impact

Design and validate probabilistic models for dynamic pricing, shipping cost estimation, recommendations, and segmentation
Design and implement Bayesian statistical models, including priors, likelihoods, and posterior inference
Build Markov chain and Hidden Markov Model formulations for sequential and behavioral patterns
Apply MCMC methods, including Metropolis-Hastings sampling, and validate convergence and sampling quality
Develop mixture models, particularly Gaussian Mixture Models, for customer or product segmentation
Implement Expectation-Maximization for latent-variable estimation and unsupervised learning tasks
Collaborate with the solution architect and client's CTO to align model design with platform architecture
Guide backend engineering on production service architecture, API design, data contracts, and microservices/event-driven integration
Define model training, validation, versioning, monitoring, drift detection, and retraining approaches
Collaborate with delivery and engineering leads to size, sequence, and estimate modeling initiatives
Document modeling assumptions, methodology, and validation results
Provide handoff guidance for ongoing engineering-team maintenance

Requirements

What you’ll need

90% English written and oral proficiency, at least B2 level
Senior-level experience communicating confidently with technical and business stakeholders, including CTO-level discussions
Demonstrable expertise in Bayesian statistical models, Markov chains, Hidden Markov Models, MCMC methods including Metropolis-Hastings sampling, mixture models (ideally Gaussian Mixture Models), and Expectation-Maximization
Experience designing statistical/ML models with production deployment in mind strongly preferred; hands-on production implementation is a plus but not mandatory
Proficiency in Python or R
Experience with probabilistic/statistical libraries such as PyMC, Stan, scikit-learn, NumPy, or SciPy
Ability to translate statistical/mathematical models into service-oriented production architecture
Understanding of APIs, data contracts, backend engineering collaboration, and architectural integration
Solid understanding of version control, testing practices, and CI/CD
Strong written and verbal communication skills
E-commerce or retail experience, especially pricing optimization, customer segmentation, or demand forecasting, preferred
Familiarity with REST/GraphQL microservices and event-driven systems preferred
Familiarity with .NET, Java, or Node.js backend ecosystems preferred
Exposure to MLOps concepts such as model registries, monitoring, or feature stores preferred
Background in pricing science, recommendation systems, or marketing analytics preferred
Experience communicating modeling recommendations to business or executive stakeholders preferred

Benefits

Comp & perks

Remote work option
Excellent work environment certified by Great Place To Work
Multicultural company environment
Opportunity to work on a 3–6 month client engagement