AmazonPosted 2mo ago

Software Development Engineer, Catalog Diagnostics (Agentic) & Analytics

Software Development Engineer, Catalog Diagnostics (Agentic) & Analytics at Amazon scores 84 out of 100 on AI centrality, which makes it AI Level 4 of 4 (Builds AI) on this board. The level measures how much of the work is AI, not seniority.

US, CA, Sunnyvalemidfull-time$165k-$224k

AI in this role

langgraphbedrock

prompt-engineeringragllm-integration

**Software Development Engineer II ** position on the Catalog Diagnostics & Analytics (CDA) team, part of Amazon's [Item and Relationship Platform](https://www.amazon.jobs) within Selection and Catalog Systems (ASCS).

At Amazon Selection and Catalog Systems (ASCS), our mission is to power the online buying experience for customers worldwide so they can find, discover, and buy any product they want. We're solving a fundamental AI challenge: establishing product identity and relationships at unprecedented scale. Using Generative AI, Visual Language Models (VLMs), and multimodal reasoning, we determine what makes each product unique and how products relate to one another across Amazon's catalog. The scale is staggering: billions of products, petabytes of multimodal data, millions of sellers, dozens of languages, and infinite product diversity — from electronics to groceries to digital content.

As an **SDE II on the IRP team**, you will take end-to-end ownership of significant features — from authoring design docs through coding, testing, deployment, and production operations. You'll work closely with Applied Scientists, Principal Engineers, and Product Managers on one of the most technically ambitious problems in e-commerce: building agentic diagnostics services that bring transparency and explainability to every change made across our catalog, backed by full data traceability.

- **Frontier AI in production**: Work with GenAI, agentic frameworks, and large-scale information retrieval applied to billions of products — not in a research lab, but in production systems serving millions of customers daily.

- **Complexity scope**: The CDA team owns one of Amazon's largest data lakes (hundreds of petabytes), serves 2,000+ internal customers, and processes catalog changes at **100K TPS**. Your work will have real, visible impact from the start.

- **Build the agentic platform from the ground up**: We are actively building our agentic diagnostics infrastructure now — you will help shape architecture decisions, not inherit a legacy system.

- **Clear growth trajectory**: Strong SDE IIs grow toward ownership of agentic platform components, mentorship of L4s, and exposure to org-level design review and cross-team technical collaboration.

Key job responsibilities
- Own complete feature development end-to-end — from design doc through coding, testing, deployment, and operational excellence in production systems handling 100K+ TPS

- Design and build **agentic architectures** that solve catalog change traceability, product identity, and relationship inference at billion-product scale using GenAI and LLM frameworks (e.g. LangGraph, Bedrock Agents)

- Build and maintain **production-grade data pipelines** that process petabytes of multimodal catalog data with rigorous evaluation frameworks for agent accuracy, resilience, and close-loop feedback

- Partner with **Applied Scientists and Principal Engineers** to translate research ideas and ambiguous business problems into scalable, maintainable engineering solutions

- Drive **technical design within your feature area** — write well-reasoned design docs, lead code reviews, and set quality standards for your workstream

- Contribute data-backed perspectives to the **team's technical roadmap**, tooling choices, and architecture patterns

- **Mentor engineers and new hires** through code review, design discussions, and day-to-day guidance

- Identify and close-loop on **production reliability challenges** at the intersection of GenAI accuracy, transactional system resilience, and large-scale information retrieval

About the team
**Catalog Diagnostics and Analytics (CDA)** team operates at a scale few engineering orgs reach:

- 🗄️ **Hundreds of petabytes** across one of Amazon's largest internal data lakes

- ⚡ **100,000 TPS** catalog change processing via a cost-effective micro-batch streaming architecture

- 👥 **2,000+ internal customers** relying on our datasets for daily business decisions

- 🤖 **Agentic platform actively under construction** — full-cycle feedback loops, agent accuracy evaluation frameworks, automated skill creation, and no-code testing and deployment lifecycle tooling

We pioneer data management technologies and architecture patterns that set standards across the broader ASCS organization. Our team culture values technical rigor, psychological safety to experiment, and close collaboration with applied science and product partners. We move fast, write clean design docs, and take pride in systems that are both innovative and production scale.

Basic qualifications

- 3+ years of non-internship professional software development experience
- 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- 1+ years of software development engineer or related occupational experience
- 1+ years of designing and developing large-scale, multi-tiered, multi-threaded, embedded or distributed software applications, tools, systems, and services using: C#, C++, Java, or Perl experience
- 1+ years of Object Oriented Design experience
- Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or a related field
- Experience programming with at least one software programming language

Preferred qualifications

- 3+ 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
- Knowledge of professional software engineering & best practices for full software development life cycle, including coding standards, software architectures, code reviews, source control management, continuous deployments, testing, and operational excellence
- Experience with generative AI technologies and AI-native development practices, including prompt engineering, LLM integration, agentic architectures, and retrieval-augmented generation. Comfortable evaluating and applying AI tools to accelerate development workflows and deliver intelligent, scalable solutions.

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 - 165,200.00 - 223,600.00 USD annually

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 IntegrationLangGraphBedrock

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?
What's a project where you used LangGraph hands-on?
Walk me through how you've used Bedrock in your day-to-day work.

Adapt your resume

List these exact terms on your resume: Prompt Engineering, Rag, Llm Integration, LangGraph, and Bedrock. 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.