Forward Deployed Engineer, Agent Runtimes & MCP (Python)

Mission. Build the Agent Trust integration into Anthropic's Claude Commerce Agents blueprint and the surrounding Claude tooling, and make it adoptable by merchant engineers in a day.
 
What you will do in the first 90 days
Stand up the blueprint's verticals on all three runtimes; run its test and verification suites; pin and maintain our fork compatibility.
Implement the AgentTrustMixin for the blueprint's StorefrontBackend / MerchantBackend: identity bound at session start, in-path trust checks on cart and checkout hooks, decision mapping to the blueprint's native tool-result semantics (Unavailable, domain errors), per-hook fail policy, decision logging without PII, outcome reporting.
Build and test the storefront MCP server path for Managed Agents behind an authenticating gateway, including vault-credential and signed-claim identity options.
Write an Customer MCP server (advisory tools) and a companion skill for the blueprint's commerce-builder Claude Code plugin.
Author the merchant integration guide and measure the merchant effort (files, lines, prompt bytes, gates, time-to-first-verified-session) as an acceptance metric.
 
Must have
 
· 5+ years Python; strong async (asyncio), typed code, pytest, ruff; comfortable subclassing abstract backends and mapping exceptions to structured results.
· Shipped tool-using LLM agents on the Claude Messages API or Agent SDK; understands prompt caching mechanics and why static-prefix bytes matter.
· Built or integrated MCP servers (streamable HTTP) and put authentication in front of them; understands that a model can skip a tool call and enforcement must live server-side.
· JWT/JWKS verification, OAuth client credentials, secrets handling; can call a real-time risk API inside a latency budget and reason about fail-open vs fail-closed.
· Reads an unfamiliar, unmaintained open-source codebase quickly and cites module and line in every claim; works from written acceptance criteria without supervision.
 
Nice to have
 
Claude Managed Agents beta (agents, environments, sessions, vaults, always_ask semantics); Claude Code plugins/skills authoring; Bedrock/Vertex/Foundry routing; e-commerce domain (cart, variants, checkout hand-off); Node 22 for the example storefronts.
 
Deliverables you own. agent-trust-commerce Python package · Managed Agents gateway variant · Customer MCP server · commerce-builder companion skill · integration guide · demo against the retail vertical.