Sr TPM, Fwd Deployed Engineer , Business Innovation and AI

We need to output HTML fragment with sections for headings: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Only include sections that have real specific content. We need to parse the description and extract content. We must not repeat job title as heading. No Job ID etc. We need to remove boilerplate: EEO, accommodation links, benefits link maybe? Benefits: The posting mentions benefits: "Amazon also offers comprehensive benefits including health insurance ... 401(k) matching, paid time off, and parental leave." Also mention sign-on payments and RSUs. So we have benefits content. Pay: The posting includes base salary ranges for two locations: Nashville and Bellevue. Also mentions sign-on payments and RSUs. So we have pay info. Schedule: Not mentioned explicitly. No schedule info. So we should not create Schedule section. Skills: Could be derived from qualifications? Might be separate. The posting includes "Experience with SQL and Python scripting", "Experience with AWS data services", etc. Those could be skills. But we have Qualifications (basic and preferred). Might combine into Requirements and Qualifications sections. The instruction: Use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we need to decide which sections to include based on content. We have About the role: The description includes a paragraph about the role: "The Forward Deployed Engineering (FDE) team within Business Innovation & AI (BIA) is looking for a Senior Technical Program Manager who builds...". That's about the role. So we can put that in About the role. Responsibilities: The "Key job responsibilities" section lists bullet points: Build AI & Agentic Solutions, Embedded; Program Delivery; Data & Data-Engineering Strategy; Raising the Bar. Also "A day in the life" narrative. So we can extract responsibilities. Requirements: Could be basic qualifications? Usually Requirements = basic qualifications. Qualifications = preferred qualifications? Or we could treat Requirements as basic qualifications, Qualifications as preferred. We'll follow that. Skills: Could be specific technical skills like SQL, Python, AWS services, agentic harnesses, etc. Might be covered in qualifications but we can still create a Skills section if we have distinct content. However we must avoid thin sections. Might be better to merge skills into Qualifications. But we need to follow instruction: Use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It says "Prefer a few substantive sections over many thin ones." So we should only create sections that have substantive content. If we can put skills within Qualifications, we might not need separate Skills section. However we have both Basic Qualifications and Preferred Qualifications; we could treat Requirements as Basic Qualifications, Qualifications as Preferred Qualifications. Then Skills might be redundant. So we can omit Skills. Benefits: We have benefits content. Pay: We have salary ranges. Schedule: none -> omit. Thus sections: About the role, Responsibilities, Requirements (Basic Qualifications), Qualifications (Preferred Qualifications), Benefits, Pay. Now we need to format with

for each heading. Use

• for any list of duties/requirements/benefits. Use

  for prose. We must preserve ALL substantive information; do not invent or summarize away detail. So we need to include all details from the posting, but we can format them as lists or paragraphs. We need to be careful not to omit any detail. Let's extract all substantive content. First, About the role: The description starts: "Description The Forward Deployed Engineering (FDE) team within Business Innovation & AI (BIA) is looking for a Senior Technical Program Manager who builds. FDE embeds directly with teams across Amazon Global Operations Services (GOS), co-builds with them from day one, and ships working AI-powered solutions. Engagements range from short builds to multi-quarter programs. The impact here is internal: you build for the GOS org, not for external customers. We increasingly look for opportunities to replace manual processes and web-based interfaces with AI agents, so a lot of what you build will be agentic. This is an FDE role first, with a data engineering edge. The core of the job is building AI and agentic solutions embedded with operational teams. On top of that, you own the team’s data and data-engineering strategy and infrastructure, the pipelines and architecture and data-quality decisions our AI work depends on. This is a builder role. We’re looking for people who are already shipping AI solutions with the current generation of tooling, not people who are newly exploring AI or have only done some prompt engineering. The engineers who do well here are hands-on with agentic harnesses like Claude Code, Kiro, and Codex, and are plugged into the AI builder community closely enough to know what changed this month." We need to preserve all that. We'll put in

  maybe multiple paragraphs. Responsibilities: The "Key job responsibilities" section includes: - Build AI & Agentic Solutions, Embedded (the primary work) * Embed with GOS operational teams, co-build from day one, and ship AI-powered solutions that change how work gets done * Look for opportunities to replace manual processes and web-based interfaces with AI agents, and build those agents end to end * Build with the current AI tooling yourself, including agentic harnesses (Claude Code, Kiro, Codex), LLM application frameworks, and RAG, and take prototypes to production - Program Delivery * Drive the planning, coordination, and delivery of FDE’s AI programs, managing risk and dependencies without relying on direct authority * Turn ambiguous operational problems into shipped solutions, and own the longer-horizon programs where the answer takes more than one build cycle - Data & Data-Engineering Strategy (the DE edge) * Own the team’s data and data-engineering strategy and infrastructure: the architecture, technology choices, and roadmap our AI work depends on * Make the calls on how operational data becomes AI-ready, and keep data quality, lineage, and freshness where the team can trust it * Connect source data to what the customer actually needs: find the right source, get the subscription in place, and build the pipeline that keeps it flowing * Make and defend the opinionated architecture calls (lakehouse vs. warehouse, batch vs. streaming, how far to normalize a domain), grounded in each use case - Raising the Bar * Define the reusable patterns and standards that raise the bar for the whole team, and mentor engineers on them Also "A day in the life" narrative: "You start the morning embedded with an operations team, working through a manual workflow you’re replacing with an agent. By mid-morning you’re building against it with current tooling and putting the next iteration in front of them. In the afternoon you switch to the data side, making the call on how a new data domain gets modeled and subscribed into the platform so the agent has what it needs. You close the day reviewing a teammate’s design against the patterns you set, and re-cutting the roadmap for a program that has two quarters left to run." We should include that as part of responsibilities maybe as a paragraph. Now Requirements (Basic Qualifications): - 5+ years of technical program management experience - Experience developing, deploying and managing AI products at scale - Knowledge of data engineering pipelines, cloud solutions, ETL management, databases, visualizations and analytical platforms - Experience with SQL and Python scripting - Bachelor's degree in computer science, engineering, mathematics or equivalent, or Bachelor's degree or above in computer science, engineering, analytics, mathematics, statistics, IT or equivalent - Experience with AWS data services (S3, Glue, Athena, Redshift, or an equivalent cloud data stack) - Experience driving technical programs across multiple teams without direct authority Now Qualifications (Preferred Qualifications): - Experience defining and driving an analytics roadmap - 5+ years of data modeling experience - A track record of shipping bespoke AI and agentic solutions from scratch, and active engagement in AI builder communities - Experience building AI agents that replace manual or UI-driven workflows - Familiarity with Amazon’s internal data ecosystem (Andes, data subscriptions, and getting access to source data across orgs) - Fluency with the current GenAI tooling landscape (Amazon Bedrock, agent frameworks, LLM-powered workflows) - Experience with Infrastructure as Code (CDK, CloudFormation, Terraform) - Experience with real-time or streaming data infrastructure (Kinesis, Kafka, Flink) - Experience mentoring engineers and defining reusable patterns that scale beyond a single team Now Benefits: The posting includes: "Amazon is an equal opportunity employer ..." that's EEO, we should remove. Then: "Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner." That's boilerplate, remove. Then: "The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including 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, and parental leave. Learn more about our benefits at https://amazon.jobs/en/benefits." We need to keep benefits: health insurance details, 401(k) matching, paid time off, parental leave, sign-on payments, RSUs. Also mention "Learn more about our benefits at ..." maybe we can keep as a link? The instruction: remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. The benefits link might be considered navigation? It's a link to benefits page. Might be okay to keep? It's not boilerplate; it's a reference. But it's a link to external site. Might be considered navigation? Safer to keep the description of benefits but maybe drop the URL? The instruction says remove boilerplate, duplicated lines, and application instructions. The link is not necessarily boilerplate; it's a reference. I'd keep it as part of benefits paragraph. Now Pay: The posting includes: "USA, TN, Nashville - 141,300.00 - 191,100.00 USD annually USA, WA, Bellevue - 148,700.00 - 201,200.00 USD annually Company - Amazon.com Services LLC Job ID: A10562368". We need to keep the salary ranges. Also mention sign-on payments and RSUs already in benefits/pay? Actually sign-on payments and RSUs were mentioned earlier in benefits paragraph. We'll keep them there. We should not include Job ID or company name as heading; we can fold minor metadata into a short

  or drop it. The instruction: "do NOT put Job ID / requisition numbers as headings — fold minor metadata into a short

  or drop it." So we can include a short paragraph at the end maybe with Company and Job ID? But they said fold minor metadata into a short

  or drop it. Probably we can drop it entirely as it's not substantive for the role. Safer to drop. Now we need to output only HTML fragment, no /, no markdown. We'll structure:

  About the role

  ... (the about role paragraph(s))

  Responsibilities

  • ... (maybe