Data Engineer

{
  "content_hash": "335e8571da447f1f0bacb1ff8dbda6a6b1eb0a63376a30c95129576293bfe747",
  "source_hash": "7ae974cfb2aa7d3522a6261ff377da43826e8a63026db62234be8846c7e7cd27",
  "last_changed_at": "2026-06-05T01:29:52.247Z",
  "active_status": "deleted"
}

{
  "language": "en",
  "location": {
    "raw": "Remote, Arlington, Virginia",
    "city": "Arlington",
    "region": "VA",
    "country": "United States",
    "is_remote": true,
    "confidence": 0.85
  },
  "salary_max": 125000,
  "salary_min": 115000,
  "inferred_at": "2026-06-03T07:45:30.149Z",
  "launch_scope": {
    "reason": "english_us_canada",
    "included": true,
    "language": "en",
    "location": {
      "raw": "Remote, Arlington, Virginia",
      "city": "Arlington",
      "region": "VA",
      "country": "United States",
      "is_remote": true,
      "confidence": 0.85
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": "remote",
  "salary_period": "year",
  "workplace_type": "remote",
  "salary_currency": "USD"
}

{}

{
  "id": "519905",
  "job": {
    "id": "525858",
    "division": null,
    "department": {
      "id": "39257",
      "name": "Data"
    },
    "requisition_id": "PIN0116",
    "structure_custom_group_one": null
  },
  "url": "https://nuvitek.pinpointhq.com/en/postings/13f16cc1-27d5-411b-aa38-de375d7c451a",
  "path": "/en/postings/13f16cc1-27d5-411b-aa38-de375d7c451a",
  "title": "Data Engineer",
  "benefits": "<div><!--block--><strong>Nuvitek is proud to offer a comprehensive benefits package:</strong></div><ul><li><!--block-->Medical Insurance</li><li><!--block-->Dental Insurance</li><li><!--block-->Vision Insurance</li><li><!--block-->Disability and Life Insurance</li><li><!--block-->Parental Leave</li><li><!--block-->401K</li><li><!--block-->Paid Time Off</li></ul><div><!--block--><strong>Equal Opportunity Employer Statement<br></strong>Nuvitek is an equal-opportunity employer as to all protected groups, including protected veterans and individuals with disabilities.</div>",
  "location": {
    "id": "32348",
    "city": "Arlington",
    "name": "Remote",
    "province": "Virginia",
    "postal_code": "22209"
  },
  "deadline_at": null,
  "description": "<div><!--block-->At <strong>Nüvitek,</strong> customer success is our Ethos; together, we drive transformational outcomes. We only succeed when our customers succeed. We partner with our customers to achieve business objectives by using our proven customer-centric, value-driven business practices and service delivery methodologies.<br><br>Nüvitek is seeking a highly skilled <strong>Data Engineer</strong> to support the design, development, and optimization of advanced AI and data processing solutions. This role will focus on building scalable data pipelines that power large language model (LLM) applications, including retrieval systems, document ingestion workflows, and intelligent search capabilities.<br><br></div><div><!--block-->The ideal candidate has hands-on experience with retrieval-augmented generation (RAG), contextual augmentation generation (CAG), OCR processing, vector databases, and modern AI data architectures. This role requires strong technical expertise, problem-solving skills, and the ability to work collaboratively within agile pod-based teams.<br><br></div><div><!--block--><br></div><div><!--block--><br><br><em>In assuming this position, you will be a critical contributor to meeting Nuvitek's mission: To deliver innovative, cost-effective solutions and services that enable our customers to rapidly adapt to dynamic environments.</em></div>",
  "compensation": "$115,000 - $125,000 / year",
  "reporting_to": "",
  "workplace_type": "remote",
  "benefits_header": "Benefits",
  "employment_type": "full_time",
  "workplace_type_text": "Fully remote",
  "compensation_maximum": 125000,
  "compensation_minimum": 115000,
  "compensation_visible": true,
  "employment_type_text": "Full Time",
  "key_responsibilities": "<ul><li><!--block-->Design, develop, and maintain scalable RAG/CAG pipelines for AI-powered applications</li><li><!--block-->Build and optimize document ingestion workflows for structured and unstructured data sources</li><li><!--block-->Manage and maintain vector stores to support semantic search and retrieval capabilities</li><li><!--block-->Develop OCR processing pipelines for historical and modern document collections spanning 1781–2025</li><li><!--block-->Optimize retrieval performance, relevance tuning, and ranking strategies for LLM-based systems</li><li><!--block-->Build reliable data pipelines that support integrations with large language models and AI services</li><li><!--block-->Collaborate with engineers, UX teams, product owners, and stakeholders to deliver scalable AI solutions</li><li><!--block-->Ensure data quality, integrity, security, and performance across ingestion and retrieval systems</li><li><!--block-->Implement monitoring, logging, and troubleshooting for AI and data processing workflows</li><li><!--block-->Contribute to architecture decisions, technical documentation, and engineering best practices</li><li><!--block-->Participate in agile pod-based development teams and continuous improvement initiatives</li></ul><div><!--block--><br></div>",
  "compensation_currency": "USD",
  "compensation_frequency": "year",
  "skills_knowledge_expertise": "<ul><li><!--block-->4+ years of experience in data engineering, data platform development, or AI/ML infrastructure</li><li><!--block-->Strong experience building RAG and/or CAG pipelines</li><li><!--block-->Hands-on experience with vector databases and semantic retrieval systems</li><li><!--block-->Experience developing document ingestion and OCR processing workflows</li><li><!--block-->Strong understanding of LLM integrations and AI data pipeline architectures</li><li><!--block-->Experience working with structured, semi-structured, and unstructured datasets</li><li><!--block-->Proficiency with Python and modern data engineering frameworks</li><li><!--block-->Familiarity with APIs, ETL/ELT pipelines, and distributed processing systems</li><li><!--block-->Experience building and operating data pipelines in secure federal cloud environments, including FedRAMP Moderate and Zero Trust architectures, with appropriate handling of sensitive data and Controlled Unclassified Information (CUI)</li><li><!--block-->Ability to obtain and maintain a federal Public Trust (or higher) clearance</li><li><!--block-->Strong analytical, troubleshooting, and performance optimization skills</li><li><!--block-->Ability to work effectively in agile or pod-based delivery environments</li><li><!--block-->Excellent communication and collaboration skills</li></ul><h2><!--block--><strong>It Would Be Great If You Also Had</strong></h2><ul><li><!--block-->Experience working with historical archives or large-scale document digitization efforts</li><li><!--block-->Familiarity with cloud-native data platforms and AI infrastructure</li><li><!--block-->Experience with search relevance tuning and ranking optimization</li><li><!--block-->Knowledge of embedding models, chunking strategies, and retrieval optimization techniques</li><li><!--block-->Experience with containerization and orchestration technologies such as Docker and Kubernetes</li><li><!--block-->Familiarity with accessibility, governance, and secure data handling practices</li><li><!--block-->Passion for building scalable AI-driven solutions that improve user experiences and operational efficiency<br><br></li></ul><div><!--block--><br></div>",
  "key_responsibilities_header": "What You Will Do",
  "skills_knowledge_expertise_header": "What You Will Bring"
}