Software Development Engineer III, Catalog Diagnostics (Agentic) & Analytics

AI in this role

Lead technical architecture for a production-grade, agentic AI platform automating catalog diagnostics at massive scale.

llms

prompt-engineeringragllm-integrationgenerative-aiagentic-systemsdistributed-systemssoftware-architecture

At Amazon Selection and Catalog Systems (ASCS), we're solving one of the hardest AI challenges in the world: establishing product identity and relationships at unprecedented scale — billions of products, petabytes of multi-modal data, millions of sellers, dozens of languages, and infinite product diversity. Using Generative AI, Visual Language Models (VLMs), and multi-modal reasoning, we determine what makes each product unique and how products relate to one another across Amazon's catalog.

The Catalog Diagnostics & Analytics (CDA) team is at the forefront of this work. We own one of Amazon's largest data lakes (hundreds of petabytes), process catalog data at 100K+ TPS through a cost-effective micro-batch streaming architecture, and serve 2,000+ internal customers who rely on our datasets for daily business decisions. We're now building the next frontier: a production-grade, agentic AI platform that automates catalog diagnostics — delivering full data provenance, change audit trails, and explainability into every catalog change at Amazon scale.

We are looking for a Senior Software Development Engineer who can operate at the intersection of ambitious technical scope, organizational leadership, and deep expertise in GenAI and Agentic systems. If you thrive in fast-paced environments and want to push boundaries at the frontier of AI and distributed systems, we'd love to hear from you.

Key job responsibilities
- **Lead technical architecture** for CDA's agentic diagnostics platform — designing systems at the intersection of GenAI, transactional engines operating at 100K+ TPS, and large-scale information retrieval

- **Set technical direction** for how we instrument, evaluate, and close the accuracy and reliability loop for production-grade agentic AI solutions — translating ambiguous business challenges into tractable engineering frameworks

- **Drive AI-native development practices** across the team: prompt engineering, LLM integration, agentic architectures, retrieval-augmented generation (RAG), and automated evaluation and feedback loop frameworks

- **Influence without authority** — collaborate with Applied Scientists, Data Engineers, and partner teams across Amazon to define standards and patterns that others adopt

- **Own end-to-end delivery** — from design through coding, testing, deployment, and operational excellence — with full accountability for production reliability and customer impact

- **Raise the technical bar** through rigorous design and code reviews, mentorship of engineers, and establishing standards for no-code testing, deployment lifecycle tooling, and automated skill creation

- **Partner with senior leadership** to shape the roadmap, identify strategic investments, and represent CDA's technical perspective in cross-organizational forums

About the team
The Catalog Diagnostics and Analytics (CDA) team owns one of the largest data lakes within Amazon Retail, managing hundreds of petabytes through processing pipelines that push the boundaries of Amazon's technology infrastructure. We maintain foundational catalog datasets relied upon by 2000+ internal customers for day-to-day business decisions.

Our team pioneers data management technologies and architecture patterns across the organization, setting standards for others to adopt. We operate daily and hourly batch datasets alongside services processing catalog data at 100K TPS through a cost-effective micro-batch streaming architecture.

CDA also owns Catalog Diagnostics services that provide insight into catalog changes, enabling Amazon stakeholders to quickly identify and resolve catalog issues. We are building an agentic solution to automate and simplify catalog diagnostics—delivering transparency through data provenance and change audit trails that explain what changed, when, by whom, and why.

We are tackling foundational challenges in making agentic solutions production-ready, including full-cycle feedback loops, agent accuracy and evaluation frameworks, automated skill creation, and no-code testing and deployment lifecycle tooling.

Basic qualifications

- 5+ years of non-internship professional software development experience
- 5+ years of programming with at least one software programming language experience
- 5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- Experience as a mentor, tech lead or leading an engineering team

Preferred qualifications

- 5+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
- Bachelor's degree in computer science or equivalent

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.

Los Angeles County applicants: Job duties for this position include: work safely and cooperatively with other employees, supervisors, and staff; adhere to standards of excellence despite stressful conditions; communicate effectively and respectfully with employees, supervisors, and staff to ensure exceptional customer service; and follow all federal, state, and local laws and Company policies. Criminal history may have a direct, adverse, and negative relationship with some of the material job duties of this position. These include the duties and responsibilities listed above, as well as the abilities to adhere to company policies, exercise sound judgment, effectively manage stress and work safely and respectfully with others, exhibit trustworthiness and professionalism, and safeguard business operations and the Company’s reputation. Pursuant to the Los Angeles County Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.

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.

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.

USA, CA, Sunnyvale - 193,300.00 - 261,500.00 USD annually

How we score this

Software Development Engineer III, Catalog Diagnostics (Agentic) & Analytics at Amazon scores 85 out of 100 for how much of the daily work is AI. That makes it AI Level 4 of 4 (Builds AI). The level is about AI in the job, not seniority.

Classification

AI Level 4. Building AI systems is the job itself: without AI, the role would not exist.

AI Level 480 to 100
AI Level 360 to 79
AI Level 240 to 59
AI Level 10 to 39

Bands come from how often the tools, models and workflows of the role are named in the posting itself. Open the description and count.

Prepare for this job

A free preview built only from this posting: what it asks for, what you could be asked in an interview, and how to adjust your resume.

Skills and AI tools this role asks for

Prompt EngineeringRAGLLM IntegrationGenerative AIAgentic SystemsDistributed SystemsSoftware ArchitectureLLMs

Questions you could be asked

How do you structure and test a prompt to get consistent output from a language model?
How would you design a retrieval step so the model answers from real data instead of guessing?
How have you integrated a large language model into a production application?
Tell me about a project where generative ai was part of your work. What did you do?
Tell me about a project where agentic systems was part of your work. What did you do?

Adapt your resume

List these exact terms on your resume: Prompt Engineering, RAG, LLM Integration, Generative AI, and Agentic Systems. An applicant tracking system matches the wording, not the idea.
Attach one line of real, concrete experience to at least one of them — a tool named with nothing behind it rarely survives a human read.
Lead with what you built, trained or shipped — this role is judged on the AI system itself, not the tools around it.

Want your resume actually rewritten for this job?

The free preview above is everything we have today. A full resume rewrite is not live yet and has no price set. Join the waitlist and we will email you if we open it.

Get new AI jobs at AI Level 4+ by email

One email a week with the new AI jobs at AI Level 4+, each rated AI Level 1 to 4 for how much AI is in the work. No recruiter spam, unsubscribe in one click.

Also alert me for new jobs at Amazon

Free. One email a week. Unsubscribe in one click.