Senior Data Engineer

{
  "content_hash": "1df18b5d5a14ca3e667fe426187eed4d378e59ffc5f0698437c0430c6bd9cf4f",
  "source_hash": "54818ed7a1d119ffe749db214047695c59ca7038f3d5ad85e60283d60f9a000a",
  "last_changed_at": "2026-05-29T06:56:19.577Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "Washington, DC",
    "city": "Washington",
    "region": "DC",
    "country": "United States",
    "is_remote": false,
    "confidence": 0.9
  },
  "salary_max": 150000,
  "salary_min": 115000,
  "inferred_at": "2026-06-06T19:44:36.509Z",
  "launch_scope": {
    "reason": "english_us_canada",
    "included": true,
    "language": "en",
    "location": {
      "raw": "Washington, DC",
      "city": "Washington",
      "region": "DC",
      "country": "United States",
      "is_remote": false,
      "confidence": 0.9
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": "hybrid",
  "salary_period": "year",
  "workplace_type": "hybrid",
  "salary_currency": "USD"
}

{}

{
  "lists": [
    {
      "text": "Technical Leadership & Strategy: ",
      "content": "<li>Architect and implement enterprise-grade data platforms, including data lakes, warehouses, and real-time pipelines.</li><li>Define and enforce data engineering standards, including ETL/ELT frameworks, data modeling, and quality controls.</li><li>Lead performance optimization of databases, queries, and pipelines (e.g., partitioning, indexing, cost-efficient cloud solutions).</li><li>Stay updated with emerging trends, evaluating and integrating new technologies.</li>"
    },
    {
      "text": "Data Architecture & Infrastructure:",
      "content": "<li>Design and implement scalable data architecture that ensures high availability, security, and performance.</li><li>Define best practices for data modeling, storage, retrieval, and governance.</li><li>Optimize database structures, schemas, indexing, and partitioning for efficient query performance.</li><li>Implement CI/CD for data pipelines and automate infrastructure using Infrastructure-as-Code (IaC) tools.</li>"
    },
    {
      "text": "Data Pipelines & ETL Development:",
      "content": "<li>Architect and develop end-to-end ETL/ELT pipelines for structured and unstructured data ingestion, processing, and transformation.</li><li>Automate and optimize data workflows using tools like Apache Spark, Kafka, Airflow, and dbt.</li><li>Monitor, troubleshoot, and optimize data pipeline performance.</li>"
    },
    {
      "text": "Data Governance, Security & Compliance:",
      "content": "<li>Implement data governance policies, including metadata management, lineage tracking, and role-based access control (RBAC).</li><li>Ensure compliance with data privacy regulations (e.g., GDPR, CCPA) and enforce security best practices.</li><li>Develop frameworks for data quality validation, anomaly detection, and integrity checks.</li>"
    },
    {
      "text": "Business & Stakeholder Engagement:",
      "content": "<li>Collaborate with stakeholders (clients, PMs) to translate business needs into technical specifications and scalable architectures.</li><li>Develop interactive dashboards and reporting solutions to provide actionable insights.</li>"
    },
    {
      "text": "Innovation & Mentorship:",
      "content": "<li>Lead technical discussions, workshops, and knowledge-sharing sessions within the team.</li><li>Mentor junior engineers, conduct code reviews, and set best practices.</li><li>Drive automation of data workflows, including CI/CD for pipelines and Infrastructure-as-Code (IaC) solutions.</li>"
    },
    {
      "text": "Technical Skills & Experience:",
      "content": "<li>7+ years of experience in data engineering with a proven track record of building scalable data solutions.</li><li>Expertise in SQL and relational database management systems (MySQL, PostgreSQL, Oracle).</li><li>Proficiency in Python (or similar languages) for data processing and automation.</li><li>Deep understanding of cloud platforms (AWS, GCP, Azure) and cloud-native data services:AWS (Redshift, Glue, S3)Azure (Synapse, Data Factory)GCP (BigQuery, Dataflow)</li><li>Hands-on experience with big data tools:Apache Spark, Kafka, Airflow, dbt, Snowflake, Databricks</li><li>Expertise in data modeling.</li><li>Strong knowledge of data security, governance, and compliance frameworks.</li>"
    },
    {
      "text": "Leadership & Soft Skills:",
      "content": "<li>Proven track record of leading data projects, including migrations, warehousing, and real-time analytics.</li><li>Ability to lead cross-functional teams and manage client expectations.</li><li>Strong problem-solving skills for debugging distributed systems and resolving data anomalies.</li><li>Experience with Agile/Scrum methodologies, including tools like Jira, Git.</li><li>Excellent communication and stakeholder management skills.</li>"
    },
    {
      "text": "Nice-to-Have (Bonus Skills):",
      "content": "<li>Certifications in cloud/data technologies (e.g., AWS Certified Data Analytics, Google Cloud Data Engineer).</li><li>Experience with ML pipelines (e.g., feature stores, model deployment).</li><li>Contributions to open-source data projects.</li>"
    }
  ],
  "country": "US",
  "createdAt": 1751300132863,
  "updatedAt": null,
  "categories": {
    "team": "Technology",
    "location": "Washington, DC",
    "commitment": "Full-time",
    "allLocations": [
      "Washington, DC",
      "United States"
    ]
  },
  "salaryRange": null,
  "workplaceType": "hybrid"
}