name: "Eduardo Gusmao"
role: "Senior Data Engineer | Data Platform Engineer | Cloud Data Engineer"
location: "Recife, Brazil"
contact: "eduardogade@gmail.com | github.com/eggduzao | linkedin.com/in/eduardogade"
languages: "English fluent | Portuguese native | Spanish B2 | German A2 | Finnish A1"

summary: "Data Platform Engineer with 8+ years of experience designing and operating scalable data platforms, distributed data systems, and production-grade pipelines across healthcare, life sciences, and enterprise environments. Strong expertise in Python and SQL, with hands-on experience in PySpark/Spark, Kafka-style event-driven workflows, Airflow, AWS, Docker/Kubernetes, Terraform, and CI/CD to build reliable data infrastructure and platform services."

core_expertise:
  - "Data Engineering"
  - "Data Platform Engineering"
  - "Cloud and Hybrid Data Infrastructure"
  - "Distributed Data Systems"
  - "ETL/ELT Pipelines"
  - "Data Modeling and Analytics Engineering"
  - "Data Quality and Governance"
  - "Healthcare and Life Sciences Data"
  - "Machine Learning Data Pipelines"
  - "Production Reliability and Observability"

career_profile:
  - "8+ years building scalable data platforms and distributed data systems"
  - "Production-grade ingestion, transformation, validation, observability, and internal tooling"
  - "Strong Python, SQL, PySpark/Spark, cloud, CI/CD, Docker/Kubernetes, and data quality background"
  - "Experience supporting analytics, BI, ML workflows, and mission-critical data products"
  - "Comfortable translating complex stakeholder requirements into maintainable platform capabilities"

professional_engagements:
  current:
    company: "Turku Biosciences / Brazilian Ministry of Health"
    title: "Senior Data Engineer"
    location: "Finland / Brazil"
    date: "Sep 2022 - Present"
    scope:
      - "Lead the design and delivery of a national-scale data platform for precision medicine, integrating multi-modal genomic, phenotypic, and clinical EHR data for 65,000+ individuals."
      - "Build scalable Python-based pipelines, distributed systems, PySpark/Spark workflows, Databricks-adjacent processing, HPC/SLURM execution, and API-driven ingestion workflows."
      - "Architect production-grade data platform services for regulated ingestion, validation, transformation, governance, PII-compliant processing, reproducible workflows, and quality/reliability controls."
      - "Develop high-performance processing and modeling layers using Python, SQL, PySpark, partitioning strategies, Parquet formats, and distributed query tuning."
      - "Design reusable integration layers and backend data services connecting heterogeneous clinical, genomic, and ERP/SAP data sources."
      - "Enable event-driven workflows, orchestration patterns, and batch/streaming-adjacent pipelines supporting analytics, BI, and ML systems."
      - "Collaborate with product, analytics, engineering, and infrastructure stakeholders to deliver platform capabilities, CI/CD, Docker/Kubernetes workloads, observability, logging, alerting, and performance tuning."
    outcomes:
      - "Integrated precision-medicine datasets for 65,000+ individuals."
      - "Improved pipeline efficiency by approximately 25%."
      - "Reduced storage costs by approximately 80%."
      - "Enabled more than 40% faster data delivery for downstream analytics, BI, and ML systems."

  previous_mid:
    company: "Göttingen General Hospital"
    title: "Data Engineer II"
    location: "Germany"
    date: "Mar 2019 - Sep 2022"
    scope:
      - "Designed and implemented scalable data platform services using Python and SQL on cloud and hybrid environments."
      - "Enabled reliable ingestion, transformation, and low-latency access for downstream analytics, BI, and application workloads."
      - "Developed and optimized high-performance ETL/ELT pipelines with Python and PySpark, leveraging distributed processing, batch workflows, and orchestration patterns."
      - "Refactored legacy systems into modular, production-grade platform services with CI/CD, automated testing, monitoring/logging, idempotency, retries, and robust error handling."
      - "Built reusable data processing frameworks and integration layers for large-scale heterogeneous datasets."
      - "Applied data modeling, validation, lifecycle standards, and governance across 12 cross-functional teams in a distributed environment."
    outcomes:
      - "Improved data availability and system responsiveness by approximately 33%."
      - "Improved reliability, maintainability, and operational efficiency by approximately 50-60%."
      - "Supported consistent data lifecycle practices across 12 cross-functional teams."

  previous_old:
    company: "Dana-Farber Cancer Institute"
    title: "Data Engineer I"
    location: "USA"
    date: "Jan 2016 - Mar 2019"
    scope:
      - "Developed cloud-native data platform services supporting large-scale drug discovery."
      - "Built Python-based ETL/ELT pipelines and API-driven integration layers for heterogeneous biomedical, operational, and financial datasets."
      - "Implemented end-to-end data processing pipelines using Python, SQL, and PySpark on Apache Spark distributed systems."
      - "Enabled scalable ingestion, transformation, validation, and batch workflows for analytics and ML-driven applications."
      - "Collaborated with product, analytics, and research stakeholders to define KPIs and translate requirements into data models, backend data logic, and reusable platform components."
      - "Contributed to production-grade data engineering practices including Git version control, validation checks, documentation, maintainable system design, reliability, and reproducibility."
    outcomes:
      - "Improved data accessibility and reduced operational costs by more than 25%."
      - "Supported analytics and ML-driven applications through reusable data platform components."
      - "Established reliable, reproducible lifecycle standards for heterogeneous biomedical and operational data."

education:
  phd_biomedical_informatics:
    degree: "Ph.D. in Biomedical Informatics"
    institution: "Harvard Medical School"
    location: "Boston / Cambridge, USA"
    date: "2013 - 2017"

  phd_computational_life_sciences:
    degree: "Ph.D. Dr. rer. nat. in Data Engineering and Computational Life Sciences"
    institution: "RWTH Aachen University"
    location: "Aachen, Germany"
    date: "2011 - 2015"

  bachelor_master_computer_science:
    degree: "B.Sc. and M.Sc. in Computer Science"
    institution: "Federal University of Pernambuco"
    location: "Recife, Brazil"
    date: "2008 - 2011"

technical_strengths:
  programming:
    primary: ["Python", "SQL", "PySpark", "Spark SQL", "Bash/Shell"]
    secondary: ["Scala", "Java", "C/C++", "YAML", "HCL"]
   : ["REST APIs", "Async programming", "Data serialization", "Production-grade software engineering", "Parquet", "JSON"]

  data_platform_engineering:
    capabilities: ["Scalable data platforms", "Distributed data systems", "Internal data tooling", "Reusable ingestion frameworks", "Transformation layers", "Platform APIs", "Developer-facing abstractions", "Self-service data capabilities", "Analytics enablement", "ML workflow support", "BI workload support"]

  distributed_data_systems:
    tools: ["PySpark", "Apache Spark", "Pandas", "Polars", "NumPy"]
    capabilities: ["Large-scale processing", "Distributed compute", "Performance tuning", "Partitioning", "Query optimization", "Resource efficiency", "Batch pipelines", "Streaming-adjacent pipelines", "Kafka", "Spark Streaming patterns"]

  cloud_hybrid_infrastructure:
    cloud: ["AWS", "Azure", "GCP"]
    infrastructure: ["HPC/SLURM", "Docker", "Kubernetes", "Terraform", "GitHub Actions", "GitLab CI"]
    capabilities: ["Cloud-native data infrastructure", "Hybrid data infrastructure", "Infrastructure-aware engineering", "Containerized workloads", "Deployment environments", "Scalable platform operations"]

  hadoop_on_prem_ecosystems:
    technologies: ["HDFS", "YARN", "Hive", "Kerberos"]
    capabilities: ["Distributed storage patterns", "Distributed compute patterns", "Legacy-to-modern platform evolution", "Secure access-controlled data environments"]

  data_modeling_tooling:
   : ["Dimensional modeling", "Semantic modeling", "Schema design", "Metadata management", "Transformation layers", "Data contracts", "Lineage", "Modeling standards", "Analytics enablement", "Platform consistency"]
    tools: ["dbt", "BigQuery", "PostgreSQL", "Parquet", "JSON"]

  software_engineering_devops_reliability:
    tools: ["Git", "GitHub", "GitHub Actions", "GitLab CI", "Docker", "Kubernetes", "Terraform"]
    practices: ["CI/CD pipelines", "Automated testing", "Deployment automation", "Monitoring", "Logging", "Alerting", "Observability", "Incident response", "Idempotency", "Retries", "SLA/SLO thinking", "Fault-tolerant design"]

  machine_learning_data_pipelines:
    capabilities: ["ML pipelines", "MLOps", "Feature engineering", "Data preparation", "Personalization workflows", "AI-enabled data workflows", "Production-oriented ML data support"]
    ai_llm: ["LLM APIs", "Embedding pipelines", "RAG", "Hugging Face"]

  data_security_governance_quality:
    capabilities: ["Data privacy", "PII-aware processing", "Compliance-aware pipelines", "Access control", "Validation strategies", "Auditability", "Data quality checks", "Governance practices", "Secure data lifecycle management", "Reliability controls", "Consistency checks"]

  processes_collaboration:
    practices: ["High-ownership engineering mindset", "Agile/Scrum", "Cross-functional collaboration", "Stakeholder enablement", "Requirements translation", "Technical documentation", "Platform capability delivery"]
    collaborators: ["Analysts", "Data scientists", "Engineers", "Product teams", "Infrastructure teams", "Security teams"]

development_environment:
  hardware: ["Apple Silicon", "ARM", "Intel", "NVIDIA GPU environments", "HPC clusters"]

  operating_systems: ["macOS", "Ubuntu", "Debian", "Fedora", "Windows"]

  infrastructure:
    cloud_computing: ["AWS", "Azure", "GCP"]
    hpc: ["SLURM", "OpenPBS", "Distributed compute environments"]
    containers: ["Docker", "Kubernetes", "Singularity"]
    infrastructure_as_code: ["Terraform", "HCL", "Cloud deployment"]

  languages:
    data_engineering: ["Python", "SQL", "PySpark", "Spark SQL", "Bash/Shell"]
    systems_and_general: ["C/C++", "Java", "Scala"]
    markup_and_config: ["YAML", "Markdown", "LaTeX", "HTML/CSS", "HCL"]

  data_stack:
    distributed_processing: ["Apache Spark", "PySpark", "Spark SQL", "Pandas", "Polars", "NumPy"]
    storage_formats: ["Parquet", "JSON", "CSV", "HDF5"]
    databases_and_warehouses: ["BigQuery", "PostgreSQL", "MongoDB", "DynamoDB", "Relational databases", "NoSQL databases"]
    modeling_and_quality: ["Dimensional modeling", "Semantic modeling", "Schema design", "Data contracts", "Lineage", "Validation checks", "Data quality checks", "dbt"]

  ml_ai_stack:
    frameworks_and_tools: ["PyTorch", "TensorFlow", "Keras", "Scikit-Learn", "Hugging Face", "NLTK"]
    workflows: ["ML pipelines", "MLOps", "Feature engineering", "Embedding pipelines", "RAG", "LLM APIs"]

  systems_tooling:
    version_control: ["Git", "GitHub"]
    packaging_and_environments: ["pip", "poetry", "micromamba", "mamba", "conda", "npm"]
    ci_cd: ["GitHub Actions", "GitLab CI"]
    observability: ["Logging", "Monitoring", "Alerting", "Observability", "Prometheus", "Grafana"]

github_positioning:
  short_pitch: "I build reliable data platforms, distributed pipelines, and production-ready data systems for analytics, BI, ML, and healthcare/life-sciences workloads."
  engineering_style:
    - "Clean, maintainable, typed Python"
    - "Data quality and reliability first"
    - "Production-aware platform design"
    - "Reproducible workflows"
    - "Strong documentation"
    - "Pragmatic cloud and hybrid infrastructure"