Specialist, Engineering (Hybrid)

We need to output HTML fragment with sections: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Only include sections that have real specific content. We must not repeat job title as heading. Must not include Job ID etc. Must preserve all substantive info. Remove boilerplate. We need to parse the job description and extract content for each section. Let's identify sections: - About the role: The initial paragraphs describing mission, role, etc. Could be considered "About the role". We'll put that in

About the role

with

paragraphs. - Responsibilities: The "Primary Activities & Responsibilities Include" bullet list. We'll put under

Responsibilities

with

• items. - Requirements: The "Required Experience And Skills" section includes experience, core programming, data engineering, agentic AI, software engineering practices, testing, API, BI, collaboration. Could be considered Requirements. We'll put under

  Requirements

  with
  • . - Qualifications: Education section: Bachelor's degree required, location info maybe? Could be Qualifications. We'll put under

    Qualifications

    with

    for degree and location. - Skills: There's a "Required Skills" list and "Preferred Skills". Could be Skills section. We'll combine required and preferred? Might be separate but we can put under Skills with both required and preferred lists. However we need to avoid duplication. The posting includes "Required Skills API Development, Automation Systems, Bioprocessing, cGMP Compliance, Computerized Maintenance Management Systems (CMMS), Data Analysis, Data Modeling, Data Pipelines, Data Storage Systems, Data Structures, Deployment Management, GitHub, JavaScript Object Notation (JSON), Learning Agility, Python (Programming Language), SQL Databases Preferred Skills Current Employees apply HERE Current Contingent Workers apply HERE US And Puerto Rico Residents Only ..." Actually that part seems garbled. The "Required Skills" list is a long list. Then "Preferred Skills" maybe later? There's also "Current Employees apply HERE" etc which is application instruction, to be removed. So we need to extract the required skills list and maybe preferred skills list (maybe none). We'll include Skills section with required skills as

    • . Might also include preferred skills if any; but the text after "Preferred Skills" seems to be navigation links. We'll ignore. - Benefits: The posting mentions "We offer a comprehensive package of benefits. Available benefits include medical, dental, vision healthcare and other insurance benefits (for employee and family), retirement benefits, including 401(k), paid holidays, vacation, and compassionate and sick days." Also mention annual bonus and long-term incentive. So we can include Benefits section. - Pay: Salary range given: $87,300.00 - $137,400.00. Also mention eligibility for annual bonus and long-term incentive. So we can include Pay section. - Schedule: Not explicitly mentioned. There's "Travel Requirements 10% Flexible Work Arrangements Hybrid Shift Not Indicated". That indicates schedule: hybrid, 10% travel, flexible work arrangements. So we can include Schedule section with that info. We must not include sections with filler like "commensurate with experience". We have real content. Now we need to output only HTML fragment, no /, no markdown fences. We'll structure:

      About the role

      ... paragraphs ...

      Responsibilities

      • ... each bullet ...
      Similarly for Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We need to preserve all substantive information; do not invent or summarize away detail. So we need to keep the details as close as possible. Let's extract About the role content: From start: "Job Description Specialist, Digital Operations Agentic Intelligence (m/f/d) Digital is the multiplier that will allow Development Sciences and Clinical Supply (DSCS) to deliver better experiments faster, efficient filing and launch, more robust supply chains and higher-confidence decisions across the portfolio. The DSCS Digital Technologies (DDT) organization is tasked with the mission to pioneer and deploy innovative digital technologies that drive the acquisition, automation and utilization of data to enhance insights, efficiency, and quality of DSCS processes and methods. The Specialist, Digital Operations Agentic Intelligence, is a hands-on technical contributor within the Agentic Intelligence team. This role supports the organization’s shift from traditional business intelligence and manual reporting toward governed, AI-ready data foundations and production-grade intelligent agents. The Specialist will contribute to the design, build, testing, documentation, and operationalization of agents, data products, automations, and reporting solutions using modern data engineering, low code/pro-code agent platforms, and disciplined software development practices. This role is intended for a technically strong early-career professional who can build with direction, learn quickly, follow engineering standards, and contribute to reusable agent patterns, governed data foundations, evaluation frameworks, and secure deployment practices. The Specialist will work across tools such as Python, SQL, Databricks, Dataverse, Power BI, GitHub, Copilot Studio, Gemini/Vertex AI or comparable enterprise AI platforms, and Microsoft Power Platform." We should not repeat the job title as heading, but we can keep the description. We'll remove the "Job Description Specialist, Digital Operations Agentic Intelligence (m/f/d)" maybe as it's title. But we can keep the rest. We'll start after that. Thus About the role paragraph(s) will be: "Digital is the multiplier that will allow Development Sciences and Clinical Supply (DSCS) to deliver better experiments faster, efficient filing and launch, more robust supply chains and higher-confidence decisions across the portfolio. The DSCS Digital Technologies (DDT) organization is tasked with the mission to pioneer and deploy innovative digital technologies that drive the acquisition, automation and utilization of data to enhance insights, efficiency, and quality of DSCS processes and methods. The Specialist, Digital Operations Agentic Intelligence, is a hands-on technical contributor within the Agentic Intelligence team. This role supports the organization’s shift from traditional business intelligence and manual reporting toward governed, AI-ready data foundations and production-grade intelligent agents. The Specialist will contribute to the design, build, testing, documentation, and operationalization of agents, data products, automations, and reporting solutions using modern data engineering, low code/pro-code agent platforms, and disciplined software development practices. This role is intended for a technically strong early-career professional who can build with direction, learn quickly, follow engineering standards, and contribute to reusable agent patterns, governed data foundations, evaluation frameworks, and secure deployment practices. The Specialist will work across tools such as Python, SQL, Databricks, Dataverse, Power BI, GitHub, Copilot Studio, Gemini/Vertex AI or comparable enterprise AI platforms, and Microsoft Power Platform." We can split into multiple

      if needed but one is fine. Now Responsibilities: The "Primary Activities & Responsibilities Include" list with subheadings: Agentic AI Development & Governance, AI-Ready Data Foundations & Integration, BI, Web Applications & Automation, Testing, Evaluation & Release Readiness, Engineering Standards, Documentation & Enablement. Each has sentences. We'll extract each bullet as a list item. Let's capture each: - Agentic AI Development & Governance: "Support the design, build, and testing of governed agents and AI-enabled workflows using Copilot Studio, Gemini/Vertex AI or comparable enterprise AI platforms, Microsoft Power Platform, APIs, connectors, and approved data sources. Contribute to agent lifecycle activities, including intake, proof of concept, MVP readiness, deployment validation, sustainment, monitoring, and retirement." - AI-Ready Data Foundations & Integration: "Build and maintain data pipelines, curated datasets, semantic layers, and reusable data products using Python, SQL, Databricks, Dataverse, Power BI, SharePoint, and other approved enterprise platforms. Ensure data is accessible, traceable, documented, fit for purpose, and aligned with applicable governance expectations." - BI, Web Applications & Automation: "Develop and maintain dashboards, reports, web applications, Power Apps, Power Automate flows, and workflow automations that help users interact with data, submit inputs, trigger processes, review recommendations, and act on insights." - Testing, Evaluation & Release Readiness: "Create and execute test cases for agents, automations, data pipelines, and reports. Support evaluation of response quality, grounding accuracy, task success, failure modes, regression performance, monitoring needs, access controls, and responsible deployment requirements." - Engineering Standards, Documentation & Enablement: "Use GitHub, VS Code, branching, pull requests, code review, reusable templates, design notes, runbooks, decision logs, and handover materials to make solutions maintainable, reviewable, and scalable across the team." We'll put each as

    • . Now Requirements: The "Required Experience And Skills" section includes multiple bullet-like paragraphs. We'll extract each as list item. Let's parse: "Experience: 2 + years of experience in data engineering, software development, web application development, automation, data science, business intelligence, AI/ML, or a related technical role. Relevant internship, academic, research, or project experience may be considered.(M.S. with 1+ year, or B.S. with 2+ years of relevant experience)" "Core Programming & Data Skills: Hands-on experience with Python and SQL, including the ability to read, write, debug, and optimize code or queries for data transformation, analysis, automation, and reporting use cases." "Data Engineering Foundation: Working knowledge of data pipelines, data modeling, data quality checks, semantic layers, metadata, lineage, and structured data products. Experience with Databricks, Dataverse, cloud data platforms, or comparable enterprise data environments is strongly preferred." "Agentic AI & LLM Application Development: Exposure to Generative AI, Large Language Models, prompt engineering, AI-enabled automation, or agentic workflow concepts through work experience, academic projects, training, hackathons, or self-directed learning. Interest in developing hands-on experience with Copilot Studio, Gemini/Vertex AI, Microsoft Power Platform, retrieval-augmented generation, workflow orchestration, and responsible AI practices." "Software Engineering Practices: Experience using GitHub or comparable source-control systems, including repositories, branching, pull requests, code review, version control, and structured documentation. Comfort working in VS Code or comparable development environments is required." "Testing, Evaluation & Governance Mindset: Ability to define test cases, validate outputs, identify failure modes, check data and answer quality, support regression testing, and understand basic principles for secure and responsible AI deployment, including access control, privacy, auditability, human oversight, monitoring, and escalation." "API, Integration & Automation Aptitude: Exposure to APIs, connectors, workflow automation, structured payloads such as JSON, permissions, service accounts, and troubleshooting integration issues are preferred." "BI, Visualization & Communication: Familiarity with Power BI or comparable BI platforms, with the ability to interpret business metrics, explain technical concepts clearly, and write concise technical documentation, user instructions, requirements, and test notes." "Collaboration & Regulated Environment Awareness: Collaborative mindset, attention to detail, willingness to learn, and familiarity with pharmaceutical, biotech, GxP, or other regulated environments." We'll make each as
    • . Now Qualifications: Education: "Bachelor’s degree in Computer Science, Data Science, Engineering, Information Technology, or equivalent experience required." Also location: "This role can be based at any of our locations at West Point, PA, Rahway, NJ or Schachen Switzerland." Also maybe "# PRD # eligibleforERP" but that's metadata, we can drop. We'll put Qualifications section with

      for degree and location maybe separate paragraphs. Now Skills: There's a "Required Skills" list: "API Development, Automation Systems, Bioprocessing, cGMP Compliance, Computerized Maintenance Management Systems (CMMS), Data Analysis, Data Modeling, Data Pipelines, Data Storage Systems, Data Structures, Deployment Management, GitHub, JavaScript Object Notation (JSON), Learning Agility, Python (Programming Language), SQL Dat