Business Intelligence Engineer, AWS DC Acqn&Construction
About the role
withparagraphs. Responsibilities: list of key job responsibilities bullet points. Use
- .
Requirements/Qualifications: Basic Qualifications list. Also Preferred Qualifications maybe separate? Could combine into Requirements section. We'll include both basic and preferred as list items.
Skills: maybe mention specific tools: SQL, Python, AWS big data tech, Tableau/Quicksight, R, SAS, Matlab, etc. Could be part of Requirements. But we can create a Skills section if there is explicit skill list. The posting includes "Experience with data visualization using Tableau, Quicksight, or similar tools", "Experience with data modeling, warehousing and building ETL pipelines", "Experience in Statistical Analysis packages such as R, SAS and Matlab", "Experience using SQL to pull data from a database or data warehouse and scripting experience (Python) to process data for modeling". Also "Experience with AWS solutions such as EC2, DynamoDB, S3, and Redshift". So we can create Skills section.
Benefits: posting mentions comprehensive benefits including health insurance, 401(k) matching, paid time off, parental leave, etc. Also mentions sign-on payments and RSUs. So we have Benefits content.
Pay: posting includes base salary range for this position: USA, VA, Herndon - 99,500.00 - 160,000.00 USD annually; USA, WA, Seattle - 99,500.00 - 160,000.00 USD annually. So we have Pay.
Schedule: not mentioned. So omit Schedule.
We must not include boilerplate like EEO, equal opportunity, accommodations, etc. Also remove duplicated lines, navigation, cookie, legal. Also remove Job ID etc. We can include minor metadata maybe as short p but not as heading. The instruction: "Do NOT put Job ID / requisition numbers as headings — fold minor metadata into a short
or drop it." We can drop it. We must preserve ALL substantive information; do not invent or summarize away detail. So we need to keep all bullet points exactly as given? We can keep them but maybe rephrase slightly? Must not invent or summarize away detail. So we should keep the content verbatim where possible, but we can format as list items. Ensure we don't lose any detail. Let's extract sections. About the role: combine the initial paragraphs up to "The ML Capacity Delivery Team (MLZ) is seeking a Business Intelligence Engineer II (BIE) ..." Actually the description includes overview of AWS Infrastructure Services, then the team description, then role specifics. We'll put all that in About the role. Responsibilities: list from "Key job responsibilities" bullet points. Requirements: Basic Qualifications list (multiple lines). Also Preferred Qualifications list. Skills: maybe we can extract from Basic/Preferred qualifications the specific tools/experience. But to avoid duplication, we could keep them under Requirements and not create separate Skills. However instruction: "Prefer a few substantive sections over many thin ones." So we could combine Requirements and Skills into one section called "Requirements & Skills". But they asked to use headings like Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We can decide to include Requirements and Skills separately if there is content. Since we have both basic qualifications and preferred qualifications, we can put them under Requirements (or Qualifications). Skills we can list under Skills. But we must not repeat content. If we put skills under Skills, we need to ensure we don't duplicate them in Requirements. We could put basic qualifications under Requirements, and preferred qualifications under Skills? Not ideal. Better: Requirements = Basic Qualifications + Preferred Qualifications (both). Skills = specific tools/experience mentioned (like SQL, Python, Tableau, etc.) but those are already in qualifications. To avoid duplication, we could treat Skills as a subset but still include them; duplication might be considered repeating detail, which is allowed? The instruction: "Preserve ALL substantive information; do NOT invent or summarize away detail." It doesn't forbid duplication, but better to avoid redundancy. However we could keep Skills section with the specific tools/experience, and Requirements section with the years of experience and degree etc. That way we split the info without duplication. Let's parse Basic Qualifications lines: - 3+ years of analyzing and interpreting data with Redshift, Oracle, NoSQL etc. experience - 1+ years of SQL, ETL or Oracle experience - 1+ years of processing large, multi-dimensional datasets from multiple sources experience - 1+ years of performing statistical analysis experience - 1+ years of developing automated reporting experience - 3+ years of in the job offered or a related occupation experience (looks like a typo; maybe "3+ years of experience in the job offered or a related occupation") - 1+ years of using SQL, ETL (Extract, Transform, Load), or Oracle experience (duplicate of earlier) - Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, Statistics, Economics, or a related field - Experience with data visualization using Tableau, Quicksight, or similar tools - Experience with data modeling, warehousing and building ETL pipelines - Experience in Statistical Analysis packages such as R, SAS and Matlab - Experience using SQL to pull data from a database or data warehouse and scripting experience (Python) to process data for modeling Preferred Qualifications: - Experience with AWS solutions such as EC2, DynamoDB, S3, and Redshift - Experience in data mining, ETL, etc. and using databases in a business environment with large-scale, complex datasets Thus we can separate: Requirements (Basic Qualifications) list items as above. Skills: list of specific tools/tech: Redshift, Oracle, NoSQL, SQL, ETL, Python, Tableau, Quicksight, R, SAS, Matlab, data modeling, warehousing, ETL pipelines, AWS solutions (EC2, DynamoDB, S3, Redshift), data mining, etc. But many overlap with requirements. To avoid duplication, we could list only those not already captured in years-of-experience bullets: like specific tools: Tableau, Quicksight, R, SAS, Matlab, EC2, DynamoDB, S3, Redshift (though Redshift already mentioned), data mining. But it's okay to have some overlap. Given the instruction to preserve all substantive information, duplication is not prohibited but might be considered unnecessary. I'd lean to include Skills section with the explicit tools/experience mentioned, and Requirements section with the years/degree etc. That way we keep all info. Benefits: list of benefits: health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, parental leave, sign-on payments, RSUs. Pay: base salary range for this position: two locations with same range. We'll output HTML fragment. Structure:
About the role
... paragraphs ...
Responsibilities
- ... ...
Requirements
- ... ...
Skills
- ... ...
Benefits
- ... ...
Pay
...
We must not include Schedule. Now craft the About the role paragraph(s). Combine the initial descriptive paragraphs: "AWS Infrastructure Services owns the design, planning, delivery, and operation of all AWS global infrastructure. In other words, we’re the people who keep the cloud running. We support all AWS data centers and all of the servers, storage, networking, power, and cooling equipment that ensure our customers have continual access to the innovation they rely on. We work on the most challenging problems, with thousands of variables impacting the supply chain — and we’re looking for talented people who want to help. You’ll join a diverse team of technical program managers, design engineers, construction managers, network engineers, supply chain specialists, security experts, operations managers, and other vital roles. You’ll collaborate with people across AWS to help us deliver the highest standards for safety and security while providing seemingly infinite capacity at the lowest possible cost for our customers. And you’ll experience an inclusive culture that welcomes bold ideas and empowers you to own them to completion. Do you want to be an integral part of the world's transition to the cloud? The ML Capacity Delivery Team (MLZ) is seeking a Business Intelligence Engineer II (BIE) with a combination of superior analytical abilities, business acumen, curiosity, technical skills, and strong written and verbal communication skills to join our team. The MLZ team is responsible for delivering ML and AI infrastructure capacity across AWS's global data center footprint. As a BIE on this team, you will build the data foundations, reporting systems, and analytical capabilities that enable leadership to make critical decisions about how we plan, track, and deliver ML capacity at scale. You will work closely with technical program managers, systems engineers, operations teams, and planning organizations to transform complex operational data into actionable insights that drive delivery velocity and efficiency. Data-driven decision-making is at the core of Amazon's culture, and people who are exceptionally talented at analyzing large sets of data to build insights are critical. Your work will directly impact the decisions and strategy of the ML Capacity Delivery organization and our customers. You will gather customer needs and insights, mine large and diverse data sets from across AWS Infrastructure, build visualizations and tools for our business partners, and generate insights to help senior leaders make critical business decisions. The successful BIE will not only possess the expertise and passion for analyzing data, designing metrics to measure the performance of the business, and building reporting capabilities and tools, but will also interact directly with business leaders and teams that rely on the metrics and analyses they produce. The ideal candidate must be a self-starter, comfortable with ambiguity, able to think big and be creative (while still paying careful attention to detail), and enjoy working in a fast-paced, dynamic environment. If you are excited about data, are results-oriented, and want to join a growing analytics team within Amazon — this role is for you!" We'll put that inmaybe split into multiple
for readability but not required. We'll keep as one
but could be long. It's fine. Now Responsibilities bullets: copy each bullet from "Key job responsibilities". Let's list: - Design, develop, and maintain scaled, automated, user-friendly systems, reports, and dashboards that support ML capacity delivery tracking, planning, and operational decision-making. - Build and optimize data pipelines for extraction, transformation, and loading (ETL) of data from diverse sources across AWS Infrastructure using SQL, Python, and AWS big data technologies. - Apply deep analytic and business intelligence skills to extract meaningful insights from large and complex data sets related to capacity delivery timelines, supply chain logistics, and infrastructure deployment. - Collaborate with program managers, systems engineers, and operations teams to understand business requirements and translate them into scalable data solutions and reporting capabilities. - Build data visualizations that tell the story of ML capacity delivery performance — trends, patterns, bottlenecks, and outliers — through rich, intuitive dashboards for stakeholders at all levels. - Design and track key performance metrics that measure the health and efficiency of ML capacity delivery operations, including delivery velocity, on-time performance, and pipeline throughput. - Serve as a liaison between business and technical teams to achieve the goal of providing actionable insights into current business performance and ad hoc analyses to support future improvements or innovations. - Recognize and adopt best practices in reporting and analysis: data integrity, test design, analysis,