# Sr. SDE, AWS Agentic WorkSpaces -  Forefront (Agentic Harness) at Amazon

Amazon is hiring a Sr. SDE, AWS Agentic WorkSpaces -  Forefront (Agentic Harness) in Seattle, United States. It pays $168k-$227k a year and Level rates it Builds AI ●●●●; you can [apply on Amazon](https://jobsbylevel.com/go/c14a0541-0432-462a-b226-c3412f27b508?utm_medium=ai-agent).

AI Level 4, AI centrality 93 out of 100. US, WA, Seattle.

## Details

- Company: [Amazon](https://jobsbylevel.com/companies/amazon)
- AI level: AI Level 4 (score 93 out of 100)
- Location: US, WA, Seattle
- Salary: $168k-$227k
- Posted: September 14, 2026
- Apply: https://jobsbylevel.com/go/c14a0541-0432-462a-b226-c3412f27b508?utm_medium=ai-agent
- Free CV review for this job: https://jobsbylevel.com/cv-review?job=sr-sde-aws-agentic-workspaces-forefront-agentic-harness-at-amazon-21a1bc

## Prepare for this job

The job page lists 5 likely interview questions for this offer, with a CV checklist: https://jobsbylevel.com/jobs/sr-sde-aws-agentic-workspaces-forefront-agentic-harness-at-amazon-21a1bc

## Description

AWS Applied AI Solutions (AAIS) is building toward a future where every business innovates with Amazon AI teammates. To get there, we build AI solutions that improve human capabilities and transform entire business functions. We create end-to-end products that surprise and delight out-of-the-box, making complex things easy and hard things possible, with no cloud experience required. We start with customers who embrace the future and build bridges to meet the rest where they are. We pursue ambitious opportunities with conviction, and we are looking for builders who share that mindset. Do you want to build the agentic platform that millions of administrators rely on to run their cloud desktops? The AWS WorkSpaces Forefront team is reinventing how customers discover onboard and manage WorkSpaces by embedding generative AI directly into our consoles and SDK. As a Senior Software Development Engineer you will be a key contributor to our agentic harness - the always-on platform layer that hosts our LLM agents: the agent loop and orchestration routing across a mixture of specialized experts personalization and memory tool/function calling over MCP retrieval and - a major area of focus for this role - the ranking and evaluation systems that decide what each agent surfaces and prove it's getting better over time. This is the shared substrate that powers AI experiences across multiple WorkSpaces products and you'll help shape and scale it alongside a team of strong engineers. We are a fungible mix of front-end back-end and ML/AI engineers driving higher customer conversion through AI-powered onboarding building a suite of AI capabilities into our consoles - LLM agents personalization recommendations and experimentation - and unifying our platform at the architectural level. The harness is where these come together: a mixture-of-experts agent platform on Amazon Bedrock (AgentCore/Strands) MCP servers that give agents persistent working memory and typed access to backend services a RAG-backed knowledge base for conversational Q&A ranking and relevance layers that order recommendations and retrieved context and offline/online evaluation harnesses that measure agent quality and gate every change. At Amazon we hire the best minds in technology to innovate and build on behalf of our customers. As a Senior SDE you'll lead the design and delivery of major components of the harness - with a particular emphasis on ranking and evaluation - tackle ambiguous greenfield problems where no playbook exists and raise the engineering bar across the team through design review mentorship and operational excellence. Because the harness is a multi-product platform you'll partner closely with other engineers UX and applied science across products - your work shows up in customer conversion admin productivity and the velocity of every team building on the platform. Key job responsibilities • Lead the ranking and evaluation systems for the harness - relevance and ranking of recommendations and retrieved context and the offline/online evaluation harnesses (golden datasets LLM-as-judge regression and drift detection human-in-the-loop feedback) that measure agent quality and gate changes before they reach customers. -Design the metrics and experimentation that turn agent quality into decision-grade signal (task completion recommendation acceptance conversion) and close the loop from production feedback back into ranking and model/prompt improvements. -Lead the design and delivery of other major harness components - the agent loop orchestration intent routing session and memory tool/function calling or streaming - and contribute significantly to its multi-quarter technical roadmap. -Help define the platform contracts (MCP tool interfaces identity pass-through agent-to-service seams) that let specialized expert agents and product teams build on the harness safely and independently. -Design and scale parts of a mixture-of-experts agent architecture on Amazon Bedrock

The description is cut here. Read the full offer: https://jobsbylevel.com/jobs/sr-sde-aws-agentic-workspaces-forefront-agentic-harness-at-amazon-21a1bc

Source: https://jobsbylevel.com/jobs/sr-sde-aws-agentic-workspaces-forefront-agentic-harness-at-amazon-21a1bc

## Cite this page

Level. https://jobsbylevel.com/jobs/sr-sde-aws-agentic-workspaces-forefront-agentic-harness-at-amazon-21a1bc.

Get job alerts: https://jobsbylevel.com/newsletter