Advisory Software Engineer

About the role

The AI CoE builds and ships agentic AI systems that sit on top of our core product APIs - a Copilot platform on Amazon Bedrock AgentCore, MCP-based tool servers, and AI advisors embedded in our shipping products. This role owns the backlog and the delivery cadence for that work. You are the single throat to choke for what the team builds next and the reason the team can build it without friction.

What you'll do

• Own and groom the backlog for one or more AI pods (agent platform, AI advisor products, or AI productivity tooling). Set sprint goals that ladder to quarterly outcomes
• Translate ambiguous executive intent ("we need an agent that helps SMBs ship smarter") into epics, stories, and acceptance criteria engineers can start on Monday
• Write acceptance criteria for probabilistic systems: define what "good" means for an agent response, what the eval set is, what the pass threshold is
• Own the definition of done for agent capabilities - including evals, guardrails, observability, cost per interaction, and rollback path, not just "the happy path works."
• Maintain the tool and capability catalog for the agent platform - which APIs are exposed as agent tools, which are approval-gated, which are read-only, and why

What you need

• 6–8 yrs of experience
• Python
• Java
• AWS
• LLMs
• Agile
• Incident response
• Any graduate

Good to have

• Machine learning
• Azure
• Snowflake
• Prototyping
• Plumbing
• Instrumentation