Forward Deployed Engineer/ Architect (with Oauth, UCP, MCP, AgentSDk exp)

Title: Forward Deployed Engineer, Agent Runtimes & MCP (Python)
Duration: 6+ months
Location: Remote
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.
====================
Title: Forward Deployed Solutions Architect
Duration: 6+ months
Location: Remote
Mission. Own the technical solution end-to-end: decide *where* trust is enforced in each ecosystem, write the architecture decision records, design the demos, and be the technical face to merchants and partners (Anthropic, Google/UCP, Cloudflare, Visa, wallet vendors).
What you will do in the first 90 days
· Produce the hook-point inventory and runtime comparison for Anthropic's blueprint (Messages API vs Agent SDK vs Managed Agents) and author two ADRs: primary runtime target and integration architecture.
· Design the reference integration: session-start identity binding, backend-level decisioning (approve / step-up / deny) with fail-open/closed policy per hook, and the gateway verifier for hosted agents — so the merchant changes zero prompt bytes and zero gate code.
· Design loyalty-without-login on UCP (namespaced signal with a loyalty block, member pricing and reserved inventory in the checkout, step-up via identity linking) and on a protocol-agnostic header/middleware rail.
· Shape the Verifiable Credential POC: issuer, holder wallet, presentation flow, merchant verifier, and the privacy properties it must demonstrate.
· Write the threat model for each integration, the merchant integration guides, and the demo runbooks with fallbacks. Run the demos.
Must have
· 8+ years in solutions or software architecture with hands-on code; recent (2025–26) production work on LLM agent systems with tool use.
· Working knowledge of Anthropic's Claude platform (Messages API tool use, prompt caching, Agent SDK, Managed Agents) and the Model Context Protocol, including authenticated MCP servers.
· Identity and payments architecture: OAuth 2.0 / OIDC, JWT/JWKS, HTTP message signatures, PCI-adjacent checkout flows; familiarity with agentic-commerce protocols (UCP, OpenAI ACP, AP2) and KYA concepts.
· Threat-modelling and privacy-by-design experience; can write an ADR that engineers actually follow and a sequence diagram a partner can read.
· Consulting-grade communication: has led technical working sessions with external engineering teams and translated between executives and builders.
Nice to have
Verifiable Credentials (W3C VC 2.0, OID4VCI/OID4VP, SD-JWT or BBS+); fraud/risk decisioning platforms; CDN/edge architectures (Cloudflare Workers); prior forward-deployed or FDE role.
Deliverables you own. ADRs · hook-point inventory · threat models · reference architecture diagrams · integration guides · demo runbooks · partner technical briefings

Work arrangement
Yes