Software Development Engineer, Ads Console Frameworks

AI in this role

prompt-engineeringai-agents

We're building the platform that powers the Amazon Ads Console — the framework layer that drives development velocity, latency, and availability improvements for tens of product teams building advertising experiences. As the console transitions toward agentic, AI-driven workflows, we need a Senior SDE to lead the technical evolution of our platform and the new systems that will underpin this shift.

The Ads Console Frameworks team owns Pantheon (the app framework powering the console's architecture), Argus (an agentic quality evaluation platform that autonomously walks advertiser workflows to detect regressions), Compass (a self-serve product analytics platform for the console), and the shared services and components that every Ads Console page depends on. Our systems serve as the foundation dozens of teams build on.

This is not a heads-down coding role. You'll drive architectural decisions with broad ambiguity — designing how the console's frameworkS evolve to support agentic development patterns, defining how product analytics should work across 141 pages, and shaping platform contracts that other teams adopt. You'll need strong product instincts to understand advertiser workflows and form a point of view on where framework-level solutions unlock the most leverage, and either bring knowledge of the advertising business or the curiosity to develop it quickly.

The role spans technically complex domains — from front-end framework architecture and module systems, through platform services targeting 99.99% availability under peak load, to AI agent orchestration, evaluation systems, and governed data pipelines. You'll also be expected to embrace and advance AI-native development practices, using AI tools and agentic coding techniques to accelerate how the team builds software. This is a horizontal team role: you set technical direction that other teams build on, define API contracts and integration patterns across organizational boundaries, and maintain platform quality as adoption scales rapidly.

The right candidate has designed and built platform systems at scale, can operate independently in highly ambiguous problem spaces, has recent hands-on experience with AI-powered or agent-oriented systems, and brings product thinking to every technical decision.

Key job responsibilities
- Lead technical architecture and hands-on delivery across the full AI application stack — UI, services, agent infrastructure, orchestration, and evaluation — for the Ads Agent experience and integration framework used by dozens of partner teams.
- Bring product thinking to every technical decision: develop deep understanding of advertiser workflows so architecture choices reflect how advertisers actually use the product.
- Set architectural direction on a horizontal platform team: define integration patterns and API contracts that dozens of teams build on, lead design reviews, and maintain quality as adoption scales.
- Establish and exemplify best practices for building AI applications (evaluation methodologies, quality guardrails, prompt engineering, orchestration patterns) and for AI-native development (using AI tools and agentic coding to accelerate the team's delivery).
- Drive operational excellence and mentor engineers across the team.

A day in the life
You start the day reviewing agent quality metrics and system health across the stack. Mid-morning you're leading a design review for a new framework capability — asking sharp questions that blend technical depth with product thinking about advertiser workflows. After lunch you're writing high-leverage code: the interface for a new extension point that partner teams will build on. Later you join a cross-team architecture discussion on whether a new capability should be a skill or a separate agent, driving alignment by making tradeoffs concrete. You close the day refactoring a service that grew complex during prototyping — because on a horizontal team, accumulated complexity compounds with every partner.

About the team
We are a team of ~50 engineers building the experience layer for the Amazon Ads Agent and Console. We own the chat interface, advertiser-facing communications, and the frameworks that enable dozens of partner teams to integrate agent capabilities across the Ads Console. This is a horizontal team — our APIs, patterns, and quality bar ripple across the organization. We're at an inflection point on two fronts: the product we build is an AI agent, and our development workflow is shifting to AI-native practices using agentic coding. Both are core to how we operate. We value technical depth, product-minded engineering, fast iteration, and building over theorizing.

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

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

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

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, NY, New York - 158,100.00 - 213,800.00 USD annually

How we rate this

Software Development Engineer, Ads Console Frameworks at Amazon rates 64 out of 100 for how much of the daily work is AI. That makes it Works on AI (AI Level 3 of 4). The level is about AI in the job, not seniority.

Classification

Works on AI. The daily work is on AI products, without building the model.

●●●● Builds AI80 to 100
●●●○ Works on AI60 to 79
●●○○ Uses AI40 to 59
●○○○ Little AI0 to 39

Levels 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 EngineeringAI Agents

Questions you could be asked

How do you structure and test a prompt to get consistent output from a language model?
How do you decide when an AI agent can act on its own versus asking for approval first?
Describe a typical day in a role like this one: which parts run through AI directly?
If you removed AI from this role, what would be left, and how do you decide what still needs a human?

Adapt your resume

List these exact terms on your resume: Prompt Engineering and AI Agents. 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.
Show where AI is part of your daily process, not a one-off project — this role expects it to be a running habit.

Want an expert to read your CV for this job?

Free. Send your CV and the role you want next. We reply by email within 2 to 4 business days.

Get a free CV review

Get new software engineer jobs (Works on AI ●●●○ or higher) by email

One email a week with the new software engineer jobs (Works on AI ●●●○ or higher), each rated 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.