Blend is a premier AI services provider, committed to co-creating meaningful impact for its clients through the power of data science, AI, technology, and people. With a mission to fuel bold visions, Blend tackles significant challenges by seamlessly aligning human expertise with artificial intelligence. The company is dedicated to unlocking value and fostering innovation for its clients by harnessing world-class people and data-driven strategy. We believe that the power of people and AI can have a meaningful impact on your world, creating more fulfilling work and projects for our people and clients. For more information, visit www.blend360.com

As a Senior Data Scientist – Marketing Mix Modeling (MMM), you will play a critical role in designing and delivering advanced Bayesian Marketing Mix Modeling solutions that help clients optimize marketing investments, improve media effectiveness, and drive measurable business outcomes. You will develop statistical models, causal inference frameworks, and optimization solutions that enable data-driven marketing decisions across global enterprises.

This role requires deep expertise in Bayesian statistics, probabilistic programming, causal inference, optimization, and marketing analytics. You will collaborate closely with cross-functional teams, including data engineers, product owners, business stakeholders, and client leadership, to build scalable, production-ready analytics solutions.

Key Responsibilities

• Design, develop, and deploy advanced Marketing Mix Models (MMM) using Bayesian statistical methodologies.
• Build Bayesian regression models with appropriate likelihoods, priors, and hierarchical model structures.
• Develop probabilistic models using PyMC and/or Stan for marketing effectiveness measurement.
• Design and implement hierarchical Bayesian models to improve estimation across sparse or multi-level datasets.
• Develop chained and multi-stage modeling frameworks with proper uncertainty propagation using Monte Carlo simulations.
• Build optimization frameworks for marketing budget allocation using constrained nonlinear optimization techniques.
• Develop multi-objective optimization solutions balancing ROI, business constraints, and marketing objectives.
• Design and evaluate causal inference frameworks using geo experiments, Difference-in-Differences, Synthetic Control, and other quasi-experimental techniques.
• Implement adstock transformations, saturation functions (Geometric, Weibull, Hill curves), and response curve estimation for media effectiveness.
• Perform model diagnostics, posterior analysis, convergence validation, and uncertainty quantification using ArviZ and Bayesian diagnostic tools.
• Collaborate with business stakeholders to translate analytical findings into actionable marketing recommendations.
• Develop production-quality Python code, reusable modeling frameworks, and reproducible analytical workflows.
• Document modeling methodologies, assumptions, validation processes, and technical findings.
• Mentor junior data scientists and contribute to technical best practices across the organization.

Required Skills

Programming & Data Science

• Strong Python programming skills with emphasis on production-quality, reusable, and maintainable code.
• Extensive experience with:
  • Pandas
  • NumPy
  • Scikit-learn
  • SciPy
• Strong SQL skills including:
  • Complex joins
  • Window functions
  • Large-scale aggregations
  • Performance optimization
• Experience using Git and version control best practices.

Bayesian Modeling

• Strong hands-on experience building Bayesian regression models from first principles.
• Experience specifying:
  • Priors
  • Likelihood functions
  • Posterior distributions
• Practical experience with:
  • PyMC
  • Stan (preferred)
• Strong understanding of:
  • MCMC sampling
  • Hamiltonian Monte Carlo (HMC)
  • NUTS sampler
  • Posterior predictive checks
• Experience interpreting Bayesian diagnostics including:
  • R-hat
  • Effective Sample Size (ESS)
  • Divergences
  • Trace plots
• Experience using ArviZ for posterior visualization and diagnostics.

Marketing Mix Modeling

• Hands-on experience developing Marketing Mix Models (MMM).
• Experience implementing:
  • Adstock transformations
  • Saturation curves
  • Hill functions
  • Geometric adstock
  • Weibull adstock
• Experience generating media response curves and estimating marketing ROI.
• Strong understanding of marketing attribution and media effectiveness measurement.

Optimization

• Experience implementing constrained nonlinear optimization using:
  • scipy.optimize
  • CVXPY
• Experience solving:
  • Marketing budget allocation
  • Portfolio optimization
  • Channel investment optimization
• Experience balancing multiple business objectives using multi-objective optimization techniques.

Causal Inference

• Experience designing and analyzing:
  • Geo Experiments
  • Difference-in-Differences
  • Synthetic Control
  • Regression Discontinuity
• Experience calibrating experiments with statistical models.
• Strong understanding of causal attribution methodologies.

Statistical Modeling

• Strong foundation in:
  • Regression analysis
  • Probability distributions
  • Hypothesis testing
  • Forecasting
  • Model evaluation
• Experience with:
  • Piecewise regression
  • Change-point detection
  • Bayesian change-point models
  • Time-series modeling

Qualifications

• Bachelor's or Master's degree in Computer Science, Statistics, Mathematics, Data Science, Economics, Operations Research, or a related quantitative discipline.
• 5–10 years of experience in Data Science, Statistical Modeling, or Marketing Analytics.
• Proven experience building production-grade statistical and machine learning solutions.
• Experience working on enterprise-scale analytics or marketing measurement initiatives.
• Strong problem-solving, analytical thinking, and stakeholder management skills.
• Excellent written and verbal communication skills with the ability to communicate complex statistical concepts to both technical and business audiences.
• Ability to work independently with minimal supervision while proactively identifying and resolving blockers.

Nice to Have

• Experience with NumPyro or Pyro.
• Experience using MLflow for experiment tracking and model lifecycle management.
• Experience running or analyzing Geo Lift or geo-experiment studies.
• Experience with cloud platforms such as Azure, AWS, or GCP.
• Experience with Databricks, Spark, or distributed data processing.
• Exposure to media planning, marketing effectiveness, customer analytics, or retail analytics.
• Publications or contributions in Bayesian statistics, causal inference, or optimization are a plus.

Thrive & Grow with Us

Competitive Salary: Your skills and contributions are highly valued here, and we make sure your salary reflects that, rewarding you fairly for the knowledge and experience you bring to the table.

Dynamic Career Growth: Our vibrant environment offers you the opportunity to grow rapidly, providing the right tools, mentorship, and experiences to fast-track your career.

Idea Tanks: Innovation lives here. Our "Idea Tanks" are your playground to pitch, experiment, and collaborate on ideas that can shape the future.

Growth Chats: Dive into our casual "Growth Chats" where you can learn from the best—whether it's over lunch or during a laid-back session with peers, it's the perfect space to grow your skills.

Snack Zone: Stay fuelled and inspired! In our Snack Zone, you'll find a variety of snacks to keep your energy high and ideas flowing.

Recognition & Rewards: We believe great work deserves to be recognized. Expect regular Hive-Fives, shoutouts, and the chance to see your ideas come to life as part of our reward program.

Fuel Your Growth Journey with Certifications: We're all about your growth groove! Level up your skills with our support as we cover the cost of your professional certifications.