Applied AI Engineer I

We need to output HTML fragment with sections: headings using

for sections like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We must not repeat job title. We must include only sections that have real specific content. We must preserve all substantive info, not invent or summarize away detail. Remove boilerplate like cookie/navigation/legal/EEO etc. Also remove posting info like "Posting Information We provide a scheduled posting end date..." etc. Also remove "Where We Work" maybe? It contains location and schedule type; schedule type is relevant for Schedule section. Location maybe not needed as heading but could be part of a short paragraph? The instruction: do NOT put Job ID/requisition numbers as headings — fold minor metadata into a short

or drop it. Location could be considered minor metadata; we could include in a short p under maybe "About the role" or separate? But we should not create a heading for location unless it's a section like "Location". Not in list of allowed headings. So we can embed location in a paragraph. We need sections: About the role (intro paragraph), Responsibilities (list), Requirements (maybe combine Knowledge You Should Bring?), Qualifications (maybe education/experience), Skills (maybe technical skills), Benefits, Pay, Schedule. We must not create sections with filler like "commensurate with experience". We have Pay: "Position offers a starting salary range of $71,000 to $91,000 USD". That's specific, so we include Pay section. Benefits: list of benefits given. Include Benefits section. Schedule: "Schedule Type: Hybrid (4 days per week in-office / 1 day remote)." That's specific, include Schedule. Now responsibilities: many bullet-like sentences under "What You Drive At DTNA". Those are responsibilities. We'll list them as

• . Requirements/Knowledge: "Knowledge You Should Bring" includes education, experience, etc. Could be split into Qualifications (education/experience) and Skills (technical). But we can combine into Requirements maybe. However we have separate headings allowed: Requirements, Qualifications, Skills. We need to decide what to put where. We must preserve all substantive info; we can split logically. Qualifications: education (bachelor's degree in engineering, computer science, data science, or related technical field) and 0–2 years relevant experience. Skills: technical skills: foundational understanding of AI/ML, SQL, Python, REST APIs, Snowflake, version control, etc. Also awareness of responsible AI, etc. Also familiarity with collaboration tools. Requirements: maybe the "Exceptional Candidates Might Have" could be considered preferred qualifications, but we could put under Requirements as "Preferred" but we need to keep substantive info. Could treat as "Preferred Qualifications". But we only have headings: Requirements, Qualifications, Skills. We could put the base requirements under Qualifications, and the exceptional candidates under Requirements (or Skills). However the instruction: "Prefer a few substantive sections over many thin ones." So maybe we combine into two sections: Responsibilities and Qualifications (which includes education, experience, skills). But we need to include Pay, Benefits, Schedule sections as they are specific. Thus we could have sections: About the role (intro), Responsibilities, Qualifications (including education, experience, technical skills, preferred), Benefits, Pay, Schedule. We must not create a section heading if no real content. All these have content. Now we need to strip boilerplate: remove "Posting Information", "We Take Care of Our Team" maybe part of Benefits? Actually "We Take Care of Our Team Position offers a starting salary range..." includes Pay and Benefits. We'll extract Pay and Benefits. Also remove "Additional Information" about visa, background check, EEO etc. Remove. Now craft HTML. We'll start with

  About the role

  then a paragraph summarizing the role description from "Inside the Role" paragraph(s). Must preserve all substantive info; we should not summarize away detail, but we can keep the sentences as is, maybe split into multiple paragraphs but keep content. We'll copy the description: "The Engineering Quality, Safety and Compliance (EQSC) team at DTNA is at the heart of product integrity, design risk assessment, and data-driven quality improvement across vehicle development programs. EQSC works with design engineering, product validation, manufacturing, service, warranty, and cross-functional teams to improve how engineering quality work products are created, connected, governed, and used to support stronger design decisions. In this role, you will be a key contributor to the EQSC team with responsibility for improving data lifecycle practices and connecting design risk assessment with manufacturing and real-world field insights. You will support short- and long-term quality improvement strategies, translate defined AI-enabled EQSC concepts into usable workflows, and help deploy practical data and process solutions through reliable, well-governed data models and agents. This role is highly collaborative and requires the ability to work across Vehicle Level Engineering, Product Engineering, Product Validation, Manufacturing, Service, Quality, IT, and business stakeholders. The role will help operationalize the AI-enabled strategy envisioned by the leadership team across EQSC by coordinating user feedback, adoption documentation, training support, configuration inputs, and implementation readiness while preserving engineering verification ownership within the expert teams." That's the intro. Now Responsibilities: list each bullet from "What You Drive At DTNA". Let's extract each sentence starting with a verb. - Support governed data pipelines, including Snowflake-enabled datasets, by helping prepare, clean, validate, and connect requirements, specifications, validation records, vehicle compliance inputs, defect investigations, manufacturing data, service data, warranty information, and field-quality insights. - Assist with SQL queries, data models, metadata fields, and data-quality checks that improve traceability, reliability, and readiness for analytics and AI-assisted workflows. - Contribute to AI-agent implementation by helping configure workflows, retrieval patterns, prompt examples, test cases, and deployment-support materials under guidance from senior team members. - Prepare approved standards, process guidance, historical examples, compliance references, investigation learnings, and engineering knowledge content for use in AI-assisted workflows and evaluation datasets. - Help test, validate, and deploy AI-agent capabilities using approved enterprise platforms, Snowflake-enabled data assets, Microsoft 365 Copilot / Copilot Studio, APIs, and related tools. - Capture data-quality issues, manual handoffs, duplicated steps, user pain points, pilot feedback, and improvement ideas in issue-tracking or backlog tools to support practical workflow improvements. - Support analysis of connected engineering, compliance, investigation, manufacturing, service, warranty, and field data to help improve risk assessment, product-quality decisions, corrective-action follow-up, and service diagnostics. - Help measure AI-agent output quality, efficiency, token usage, user feedback, and accuracy by supporting evaluation datasets, regression testing, grounding checks, stress testing, and hallucination-reduction reviews. - Create and maintain implementation notes, prompt/configuration change logs, user guidance, training aids, data definitions, known limitations, and adoption content in Confluence, SharePoint, and similar enterprise knowledge platforms. - Work with Vehicle Engineering, Product Engineering, Vehicle Compliance, Product Validation, Manufacturing, Service, Quality, IT, defect investigation teams, and regional/global stakeholders to support user acceptance testing, adoption, and well-governed AI and data solutions. Now Qualifications: we need to include education, experience, technical skills, and maybe preferred. Let's parse "Knowledge You Should Bring" bullet list: - A bachelor’s degree in engineering, computer science, data science, or a related technical field. - 0–2 years of relevant experience through work, internships, co-ops, academic projects, or applied technical projects. - Foundational understanding of AI/ML and GenAI concepts, including large language models, embeddings, retrieval, prompt patterns, and basic model evaluation. - Awareness of responsible AI practices, including grounding, hallucination reduction, privacy, access control, bias awareness, and human review for high-impact engineering decisions. - Basic experience preparing, cleaning, validating, joining, and documenting datasets for analytics, automation, or AI-assisted workflows. - Working knowledge of SQL, Python, REST APIs, and enterprise data-platform concepts, including Snowflake or similar environments. - Familiarity with basic software-development practices such as version control, configuration tracking, code review, testing discipline, and clear technical documentation. - Evaluation and regression-testing mindset, including the ability to create test cases, compare expected and actual results, document limitations, and support issue resolution. - Familiarity with collaboration, documentation, and issue-tracking tools such as Jira, Azure DevOps, Confluence, SharePoint, or similar platforms. - Basic awareness of automotive, engineering quality, product development, compliance, manufacturing, warranty, service, or field-quality workflows. - Ability to communicate clearly, collaborate across functions, learn quickly, ask good questions, and manage multiple tasks with guidance. Then "Exceptional Candidates Might Have" list: - Applied project, internship, co-op, capstone, or portfolio experience that shows the ability to turn data or AI concepts into a working prototype, workflow, dashboard, or documented solution. - Hands-on exposure to AI-enabled workflows, custom AI agents, retrieval-augmented generation, vector search, embeddings, prompt engineering, or agent evaluation through coursework, projects, internships, or prototypes. - Practical experience using enterprise data platforms or business systems such as Snowflake, Dataverse, SAP, SharePoint, Power Platform, or similar environments to query, organize, connect, or visualize data. - Experience building simple Power BI, Excel, Python, or similar dashboards/reports to summarize usage, quality, adoption, workflow status, or data-quality metrics. - Exposure to automotive, manufacturing, warranty, service, aftermarket, vehicle compliance, defect investigation, or field-quality data and how those signals can support product-quality decisions. - Experience documenting requirements, test results, defects, user feedback, known limitations, or adoption materials in tools such as Jira, Azure DevOps, Confluence, SharePoint, or similar platforms. - Exposure to structured problem-solving, quality improvement, or engineering root-cause analysis methods. We could treat the first list as "Qualifications" and the second as "Preferred Qualifications" but we don't have a heading for Preferred. Could put under Qualifications as well, maybe separate subheading? But we cannot add extra headings beyond allowed list? The instruction: use

  for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It doesn't forbid other headings, but says use those for section headings. It might be okay to use other headings but better to stick to those. We could incorporate the exceptional candidates into Qualifications or Skills. Perhaps we put them under Skills as "Preferred skills". But we need to keep all info. Simplify: Have Qualifications section containing education, experience, and the "Knowledge You Should Bring" list. Then Skills section containing technical skills from that list plus the exceptional candidates list (maybe as "Preferred skills"). But we already have technical skills in Knowledge list; we could split: Qualifications = education + experience; Skills = technical and soft skills; and maybe add a separate "Preferred Qualifications" but we don't have heading. Could add under Skills as "Preferred skills". That seems okay. Thus:

  Qualifications

  • A bachelor’s degree in engineering, computer science, data science, or a related technical field.
  • 0–2 years of relevant experience through work, internships, co-ops, academic projects, or applied technical projects.

  Skills

  • Foundational understanding of AI/ML and GenAI concepts, including large language models, embeddings, retrieval, prompt patterns, and basic model evaluation.
  • Awareness of responsible AI practices, including grounding, hallucination reduction, privacy, access control, bias awareness, and human review for high-impact engineering decisions.
  • Basic experience preparing, cleaning, validating, joining, and documenting datasets for analytics, automation, or AI-assisted workflows.
  • Working knowledge of SQL, Python, REST APIs, and