Description

Tooling

GitHub, Jira/Confluence, Python 3.11+, Node 22 / TypeScript 5, Claude API and Claude Code (or the OpenAI API, or an equivalent model hosted on AWS Bedrock), AWS

Must have

•     7+ years Python building production microservices for typical modern SaaS backends; strong async (asyncio), typed code, pytest, ruff.

•     API security fundamentals: OAuth 2.0 (client credentials, on-behalf-of / token exchange), JWT issuance and verification, JWKS rotation and caching, secrets handling.

•     Microservices architecture experience: service-to-service auth, structured error/result handling across service boundaries, fail-open vs. fail-closed reasoning under a latency budget.

•     Reads an unfamiliar, unmaintained codebase quickly and cites module and line in every claim; works from written acceptance criteria without supervision.

Nice to have

•     OAuth token exchange (RFC 8693) in production, and can explain why forwarding the user's token downstream is unsafe (aud, scope narrowing, confused deputy); production AWS experience (Lambda or ECS, IAM, Secrets Manager).

•     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) with authentication in front of them; has built or extended an LLM evaluation harness.

•     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 · Experian MCP server · commerce-builder companion skill · integration guide · demo against the retail vertical

Key Skills

Education

Any Graduate