Hi, I’m Anderson 👋

Data Scientist | ML Engineer | Causal Inference Practitioner

I'm a data scientist and engineer focused on building robust, production-grade ML pipelines, architecting scalable DevOps workflows, and solving high-stakes problems using causal inference. My work spans experimentation platforms, predictive modeling, infrastructure automation, and analytics-driven product strategy.

Machine Learning Engineering Building modular, reproducible ML pipelines with integrated tracking (MLflow), monitoring (CloudWatch), and deployment (AWS SAM, Docker, Prefect).

Causal Inference & Experimentation Designing and analyzing A/B tests, quasi-experiments (DiD, RDD), uplift modeling, and measurement systems for marketing, product, and operational decisions.

DevOps & MLOps Automating infrastructure for data science workflows using GitHub Actions, IaC (SAM/CloudFormation), S3 for model artifact storage, and containerized microservices.

Analytics & Decision Science Deep dives into customer behavior, pricing strategies, and operational KPIs using advanced statistics, regression modeling, and Bayesian methods.

Causal Experimentation Toolkit Reusable framework for designing, running, and evaluating controlled and observational experiments with diagnostics, power analysis, and effect estimation.

Infra Scripts & Tooling Scripts, SAM templates, and container setups for rapid provisioning of dev/test environments for ML workflows—integrated with GitHub Actions for CI/CD.

• Fine-tuning and scaling ML pipelines for real-time inference
• Building modular, interpretable causal inference tools
• Experimentation strategy for product and growth teams
• MLOps best practices with emphasis on cost monitoring and observability

Want to collaborate or learn more about my work? Reach out on LinkedIn or check out the repos below.