Data Engineer, AI Enablement

We need to output HTML fragment with sections: About the role? Actually the posting includes Company Description, Job Description, Responsibilities, Qualifications, Additional Information (benefits, pay range). We need to use

for section headings like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We must not repeat job title as heading. We must include sections only when posting has real specific content. We must preserve all substantive info, not invent or summarize away detail. Remove boilerplate: cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, application instructions. Also remove "Company Description About AbbVie" maybe we can keep as a short paragraph? It's not a required heading; we can include as a

maybe under a generic "About the company"? But headings list does not include About the company; we could just put it as a

before sections. The instruction: Use

for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we can use those headings if content exists. We have Responsibilities, Qualifications (which includes Required and Preferred). We have Benefits mentioned in Additional Information. Pay range mentioned. Schedule not mentioned. Skills? Not mentioned. Skills maybe implied but not explicit separate list; we could omit Skills section if no explicit list. Requirements maybe same as Qualifications? The instruction includes Requirements as a possible heading; but we have Qualifications. We could treat Qualifications as the heading. We'll include Responsibilities, Qualifications, Benefits, Pay. Also maybe About the role? Could use About the role as a heading for the job description summary. The job description paragraph describes role. We could put that under

About the role

. That seems appropriate. We must not include duplicated lines. We'll need to extract content. Let's parse the posting: Company Description About AbbVie: mission etc. We'll keep as a short paragraph maybe under a

before sections. Job Description: paragraphs describing role. We'll put that under About the role. Responsibilities: bullet list under heading Responsibilities. Qualifications: Required and Preferred. We'll put under Qualifications. Additional Information: includes pay range, benefits, note about compensation, EEO etc. We need to keep benefits and pay range. Remove EEO boilerplate. Also remove "Applicable only to applicants applying to a position in any location with pay disclosure requirements under state or local law:" maybe keep as part of pay section? It's legal boilerplate but it's about pay disclosure; might be considered boilerplate? The instruction says remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate. This is legal boilerplate about pay disclosure; maybe we should remove it? But we need to preserve pay range. The sentence about compensation range being possible base pay etc. That's part of pay info; we can keep that but maybe it's considered legal? It's still part of pay description. We'll keep the pay range and the note that individual compensation depends on location etc. Might be okay. Benefits: "We offer a comprehensive package of benefits including paid time off (vacation, holidays, sick), medical/dental/vision insurance and 401(k) to eligible employees. This job is eligible to participate in our short-term incentive programs." Keep that. We should not include the note about "Note: No amount of pay is considered to be wages or compensation until such amount is earned, vested, and determinable." That's legal boilerplate; maybe remove. Also "The amount and availability of any bonus, commission, incentive, benefits, or any other form of compensation and benefits that are allocable to a particular employee remains in the Company's sole and absolute discretion unless and until paid and may be modified at the Company’s sole and absolute discretion, consistent with applicable law." That's legal; remove. Also EEO statements: remove. Also "Additional Information" heading we can drop; we just embed content under Benefits and Pay. Now we need to format lists: Responsibilities bullet list; Qualifications maybe split into Required and Preferred as subheadings? But we only have h3 headings allowed; we could keep Qualifications as h3 and inside have

for required and

for preferred, or use

• for each list. The qualifications are paragraphs; we could keep as

  . But we have list-like items separated by periods. Might be okay as

  . However instruction: Use

  • for any list of duties/requirements/benefits. So for Responsibilities we need
    • . For Qualifications we have required and preferred; each is a list of items separated by semicolons? Actually it's a paragraph with many items separated by periods. Could treat as

      . But to be safe, we could split into

      • for each distinct requirement? That might be too granular but still a list. However the instruction says "any list of duties/requirements/benefits". The qualifications section is a list of requirements; we could make a
        • for each bullet. But the source doesn't have bullet formatting; it's a paragraph. We could still convert each sentence to a
        • . That would preserve all info. Let's do that. Similarly for Benefits we have a list: paid time off, medical/dental/vision insurance, 401(k), short-term incentive programs. We'll make
          • . Pay: we have a range: maybe we need to extract the range. The text: "The compensation range described below is the range of possible base pay compensation that the Company believes in good faith it will pay for this role at the time of this posting based on the job grade for this position." No actual numbers given! Actually they didn't provide numbers. So there is no specific pay range; it's just a statement. Since we must not create Pay section unless posting actually states them. It does not state numbers. So we should NOT include a Pay section. The instruction: never create Pay/Schedule/Benefits sections unless the posting actually states them. Benefits are stated (paid time off etc). So we include Benefits. Pay not stated with numbers, so we omit Pay section. Schedule not stated, omit. Now About the role: we need to include the job description paragraphs. We'll put them under

            About the role

            as

            . Now Responsibilities: we need to extract bullet points from the responsibilities section. The responsibilities are listed as sentences each starting with a bold heading? Actually they have headings like "AI-Ready Data Product Engineering:" then a sentence. We'll treat each heading+sentence as a list item. We'll produce

            • for each. Let's list them: - AI-Ready Data Product Engineering: Design, build, and operate curated, reusable data products that make high-value R&D data easier to find, connect, understand, and use. Collect, integrate, normalize, model, and transform data from databases, applications, APIs, licensed external sources, and other systems into ARCH and related data environments. - Trusted Data Foundation Enablement: Establish reliable, scalable data foundations that support analytics, reporting, knowledge graph capabilities, machine learning, and AI-enabled use cases. Ensure data assets are structured, documented, accessible, governed, traceable, and fit for downstream consumption. - AI, RAG & Knowledge Graph Readiness: Prepare data and documents for AI and knowledge discovery use cases by cleaning, standardizing, enriching, labeling, organizing metadata, supporting chunking, and embedding workflows, and producing vector database-ready assets. Enable publication of curated data to the ARCH knowledge graph. - Data Quality, Governance & Documentation: Apply data quality and governance practices, including accuracy and completeness checks, metadata, lineage, access controls, privacy, license terms, assumptions, quality rules, and appropriate-use guidance so data consumers can understand and trust the assets they use. - Technical Coordination & Delivery Support: Collaborate with data scientists, machine learning engineers, software engineers, platform teams, architects, data owners, and R&D stakeholders to translate scientific and business requirements into usable AI-ready data products. Provide technical guidance to contracted engineers, clarify work, review outputs, help remove barriers, and support delivery against agreed quality and acceptance standards. - Operational Reliability & Continuous Improvement: Monitor pipeline performance, data freshness, cost, failures, and delivery issues; troubleshoot and resolve problems before they impact data consumers. Contribute to reusable engineering patterns, automation, process improvements, and consistent ways of working across data product workflows. - Compliance & Standards: Follow applicable Corporate and Divisional policies, including GxP compliance, data security, software development lifecycle practices, data governance standards, and relevant regulatory or contractual requirements. Now Qualifications: Required and Preferred. Required: The paragraph: "Bachelor’s Degree with 5 years of experience; OR Master’s Degree with 4 years of experience in information technology, data engineering, data management, analytics, life sciences, or a related field.Hands-on experience designing, developing, and operating production data pipelines and curated data products using SQL, Python, ETL/ELT patterns, and workflow orchestration tools such as Airflow. Working knowledge of modern data platforms, data integration, data warehousing or lakehouse patterns, distributed SQL or big data environments, cloud infrastructure, and analytics enablement. Experience preparing data for downstream analytics, machine learning, knowledge graph, or retrieval use cases, including cleaning, standardization, enrichment, structuring, metadata organization, and support for embedding or vector-search workflows. Experience applying data quality, metadata management, governance, lineage, documentation, and data modeling practices to support trusted, reusable data products. Experience collaborating with cross-functional business, scientific, technical, platform, vendor, contractor, or managed-services teams to translate requirements and deliver fit-for-purpose data assets. Ability to operate with a high degree of autonomy, manage priorities across concurrent workstreams, modify approach when needed, escalate open issues, and keep stakeholders informed through clear written and verbal communication. Demonstrated ability to learn, understand, and apply new data engineering, platform, and AI-enablement technologies, and to serve as a technical resource for others. Experience providing technical input, clarifying requirements, and reviewing outputs from contracted, vendor, or managed-services engineers without direct reporting authority. Strong communication, planning, and organizational skills, with the ability to explain technical concepts and keep stakeholders informed. Data product engineering mindset, with the ability to shape reusable, well-structured data assets that are practical, scalable, and fit for analytics and AI-enabled use. Data curation and stewardship mindset, with attention to quality, metadata, lineage, governance, standards, documentation, and appropriate use. Technical fluency across data platforms, pipelines, integration patterns, orchestration, cloud environments, and data delivery practices sufficient to work effectively with engineering and platform teams. Operational discipline across monitoring, troubleshooting, prioritization, issue resolution, automation, reusable patterns, and continuous improvement. Technical coordination and influence, with the ability to clarify priorities, guide work, review outputs, resolve ambiguity, and coordinate across internal and external contributors. Stakeholder communication, with the ability to frame tradeoffs, risks, dependencies, and progress in a clear and practical way for technical, scientific, and business audiences." We need to split into list items. Could break by sentences. Let's do that. Preferred: "Pharmaceutical or healthcare industry experience preferred. Experience supporting research, discovery, translational, clinical, scientific, or other life sciences data environments. Familiarity with graph databases, knowledge graphs, ontology-based data structures, semantic data, metadata-driven data products, or linked-data concepts. Experience working with AWS-based, cloud-based, lakehouse, or modern data platform technologies such as Databricks, Spark, Snowflake, Neo4j, or similar tools. Experience working with regulated data environments, including data governance, documentation, security, privacy, license terms, or compliance expectations. Exposure to analytics, machine learning, retrieval-augmented generation (RAG), embeddings, vector databases, AI-search patterns, or AI-ready data product delivery. Familiarity with Agile practices or planning tools such as Jira, including backlog refinement, sprint planning, prioritization, acceptance criteria, and delivery tracking." Now Benefits: "We offer a