AI Solutions Engineer

The user wants me to convert this job posting into clean semantic HTML. Let me analyze the content and structure it according to the rules. First, I need to identify the sections: - Pay rate is given: $50.00 - $54.43/hr - Summary/About the role - Responsibilities (with subsections) - Qualifications - Skills - Benefits (mentioned in pay transparency section) - Schedule (full-time mentioned) I should use

for section headings,

• for lists,

  for prose. Rules: - No job title heading (already shown on page) - No Job ID/requisition numbers as headings (fold into short

  or drop) - Preserve ALL substantive information - Remove boilerplate (cookie/navigation/legal/EEO/scam-warning, duplicated lines, application instructions) - Include section ONLY when real specific content exists - Never emit heading followed by filler/placeholder text - Never create Pay/Schedule/Benefits sections unless posting actually states them - Output ONLY HTML fragment, no /, no markdown code fences Let me structure: 1. Pay section - the posting states pay rate clearly, so include Pay section. 2. About the role / Summary - use "About the role" as heading. 3. Responsibilities - with subsections? The responsibilities are grouped into four areas: AI Application and Software Engineering, Data Engineering and Automated Quality Control, Software Quality and Reproducibility, Responsible AI and Governance. Should I make each a subheading? The rule says use

  for section headings. Could use

  for subsections? But the instruction says use

  for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It doesn't mention subheadings. However, the responsibilities have clear subsections. I could make them

  or just include as part of the responsibilities list. But the instruction says use

  • for any list of duties/requirements/benefits. The responsibilities are listed as bullet points under each subsection. I think I should keep the subsections as headings (maybe

    ) but the instruction only mentions

    . However, the example includes "Responsibilities" as a heading. The subsections are part of responsibilities. I could make them

    but the instruction doesn't forbid other heading levels. It says "use

    for section headings". It doesn't say you cannot use other headings. But to be safe, I'll use

    for main sections and maybe

    for subsections. However, the output should be a fragment, so using

    is fine. But the instruction says "use

    for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." That suggests those are the only section headings. The subsections might be considered part of the Responsibilities section. I could list all responsibilities as a single list with sub-bullets? But the posting has distinct categories. I think it's better to include them as subheadings (maybe

    ) to preserve structure. The instruction says "Preserve ALL substantive information". The categorization is substantive. I'll use

    for the four responsibility areas. Similarly, Qualifications and Skills are separate sections. The posting has "Qualifications" and "Skills" as separate headings. I'll use

    for each. Benefits are described in the pay transparency section. I'll create a Benefits section. Schedule: mentions "Full-time employees are eligible..." and "Non-exempt positions are eligible for overtime...". That's schedule info. I'll include a Schedule section. Also there's a "Pay Transparency" section with pay details. I'll include Pay section. Now, the Job ID: "#AditiConsulting # 26 - 06795" at the end. That's a requisition number. Should fold into a short

    or drop. I'll include a brief note at the end maybe in a

    with class? But the instruction says fold minor metadata into a short

    or drop it. I'll include a

    at the end with the job ID. Also there's a long consent paragraph about communication and AI technology. That's boilerplate legal/consent. Should remove. The pay transparency section includes pay rate and benefits. I'll extract pay and benefits. Let me draft HTML. First, Pay section:

    Pay

    The typical base pay for this role across the U.S. is $50.00 - $54.43 per hour. Non-exempt positions are eligible for overtime at a rate of 1.5 times the base hourly rate for all hours worked in excess of 40 in a work week, or as required by state or local law. Final offer amounts, within the base pay set forth above, are determined by factors including your relevant skills, education and experience.

    About the role:

    About the role

    The AI Solutions Engineer will design, build, test, and maintain reusable software, data pipelines, automation, and AI-enabled applications for Translational Medicine. The successful candidate will translate requirements from business, scientific, and operational stakeholders into reliable data products, automated quality-control workflows, dashboards, and agentic AI applications. The engineer will work closely with data scientists, product owners, and enterprise technology teams to move prioritized solutions from requirements through deployment and maintenance. The role is focused on developing scalable technical products, not conducting primary data analysis or building isolated, study-specific tools. Solutions must be secure, well documented, version-controlled, reproducible, and aligned with enterprise and industry data, privacy, cybersecurity, quality, and responsible AI requirements.

    Responsibilities:

    Responsibilities

    Then subsections. I'll do:

    AI Application and Software Engineering

    • Design, develop, test, document, and maintain AI-enabled applications, dashboards, APIs, and/or workflow-automation solutions using approved models and platforms.
    • Develop modular components that can be reused across programs, studies, disease areas, and workflow types.
    • Create user-friendly applications that make governed data and computational capabilities accessible to scientific and operational users.
    • Evaluate prototypes for feasibility, reliability, scalability, maintainability, and readiness for broader deployment.
    • Implement human review, source visibility, feedback mechanisms, access controls, and appropriate transparency measures for AI-enabled products.

    Data Engineering and Automated Quality Control

    • Develop and maintain data-ingestion, transformation, reconciliation, validation, and quality-control workflows for clinical biomarker data.
    • Maintain and expand existing R-based software, ETL scripts, and automated QC capabilities.
    • Translate data-transfer specifications, scientific requirements, and business rules into executable code.
    • Develop configurable workflows that reduce repetitive setup and manual intervention across datasets and studies.
    • Produce clear reports, processing logs, QC outputs, and traceable records for scientific and operational review.
    • Preserve source values, surface unresolved exceptions, and ensure workflows fail safely.

    Software Quality and Reproducibility

    • Write maintainable, modular, tested, and appropriately documented code.
    • Use approved source-control, branching, release, and versioning practices with Git.
    • Maintain traceability among requirements, source data, code versions, tests, outputs, and releases.
    • Contribute to monitoring, logging, error handling, and operational support documentation.
    • Support risk-appropriate peer review and independent code validation.

    Responsible AI and Governance

    • Design solutions in accordance with applicable responsible AI, privacy, cybersecurity, data-rights, third-party, quality, and regulatory requirements.
    • Document solution architecture, data sources, data flows, intended users, intended use, limitations, and human-oversight mechanisms.
    • Support required AI risk triage, mitigation documentation, and technical reviews.
    • Implement and test agreed technical controls.
    • Escalate governance, privacy, security, data-rights, validation, or regulatory questions to the accountable experts.
    Qualifications:

    Qualifications

    • Bachelor's or master's degree in computer science, software engineering, data science, bioinformatics, computational biology, biomedical engineering, or a related quantitative field.
    • At least two years of professional experience developing data-intensive software, scientific applications, data pipelines, AI-enabled applications, or automation solutions in a production setting.
    • Demonstrated experience delivering software beyond exploratory notebooks or one-time analyses.
    • Experience translating stakeholder needs into technical requirements.
    • Experience testing, documenting, releasing, maintaining, and troubleshooting software.
    • Experience in life sciences, pharmaceuticals, biotechnology, clinical research, or other regulated environments.
    Skills:

    Skills

    • Proficiency in Python for application development, automation, data processing, API integration, and testing.
    • Proficiency in R, including package development or maintenance, ETL workflows, testing, and documentation.
    • Strong command of Git and GitHub, including branching and pull requests as well as release and version management.
    • Experience with code documentation, automated testing, logging, debugging, and error handling.
    • Experience developing ETL, data-validation, reconciliation, or workflow-automation solutions.
    • Working knowledge of Linux development environments.
    • Ability to communicate technical concepts to scientific and operational stakeholders.
    • Experience with clinical, multi-omics, imaging, pathology, or real-world datasets.
    • Experience building generative-AI or agentic applications, structured outputs, evaluation frameworks, or human-in-the-loop approaches.
    • Experience with Microsoft Copilot Studio.
    • Experience with AWS and/or Databricks.
    • Experience with Docker, CI/CD pipelines, and deployment automation.
    • Familiarity with SQL, relational DBs, and other data structures.
    • Experience with REST APIs and MCP.
    • Familiarity with Airflow, Nextflow, Snakemake, CWL, or other workflow platforms.
    • Understanding of data provenance, privacy, consent, regulated data, GxP considerations, and risk-based software validation.
    Benefits:

    Benefits

    Full-time employees are eligible to select from different benefits packages. Packages may include medical, dental, and vision benefits, health savings accounts with qualified medical plan enrollment, 10 paid days off, 3 days paid bereavement leave, 401(k) plan participation with employer match, life and disability insurance, commuter benefits, dependent care flexible spending account, accident insurance, critical illness insurance, hospital indemnity insurance, accommodations and reimbursement for work travel, and discretionary performance or recognition bonus. Sick leave and mobile phone reimbursement provided based on state or local law.

    Schedule:

    Schedule

    Full-time position. Non-exempt positions are eligible for overtime at a rate of 1.5 times the base hourly rate for all hours worked in excess of 40 in a work week, or as required by state or local law.

    Finally, a short

    for job ID:

    Job ID: 26-06795 (Aditi Consulting)

    But the instruction says "do NOT put Job ID / requisition numbers as headings — fold minor metadata into a short