Senior AI Software Engineer, Internal Enablement

Vaga não está no LinkedIn

🕒 Maio 6

🏄 California – Remoto

🏄 California – Remote

💵 $160.000 - $180.000 / ano

⏰ Tempo Integral

🟠 Sênior

🧑‍💻 Engenheiro Full-stack

🦅 Patrocina Visto H1B

Esta empresa já patrocinou vistos H1B no passado.

Candidatar-se

Encontrar Vagas Remotas Similares

Receber Emails de Vagas Remotas

📊 Verifique sua pontuação de currículo para esta vaga

Melhore suas chances de conseguir uma entrevista verificando sua pontuação de currículo antes de se candidatar.

Enviar Currículo

Extend

SiteLinkedInTodas as Vagas

201 - 500 funcionários

🛍️ Comércio Eletrônico

🔌 API

🤝 B2B

eCommerce • API • B2B

A Extend é uma empresa que ajuda os comerciantes a gerar receita e proteger seus clientes por meio de soluções modernas de proteção de produtos e frete. Eles oferecem planos de proteção contra falhas de produtos e danos acidentais, além de problemas de envio, como furtos em varandas e entregas danificadas. A Extend fornece uma plataforma fácil de integrar com plataformas de eCommerce como Shopify e BigCommerce, permitindo que os comerciantes ofereçam facilmente planos de proteção e gerenciem reivindicações, com a maioria sendo resolvida em 90 segundos ou menos. A empresa foca em melhorar as margens de lucro e aprimorar a experiência do cliente, oferecendo um processo fácil de registro de reivindicações e transformando clientes em defensores de longo prazo.

Descrição

• Design and ship secure MCP (Model Context Protocol) connectors to Extend's internal systems and the third-party SaaS we run on: finance, CRM, data warehouse, expense management, product analytics, support, ATS, and the long tail beyond. • Build and curate the shared library of agent skills that every team at Extend composes from. Ship skills, codify patterns, and raise the floor for what a safe, high-quality skill looks like. • Extend our agent infrastructure. Build the tooling that lets non-engineers create reusable agent skills securely and reliably. Encode the review and publishing model for shared tooling, shared runtimes, and the feedback loop on agent behavior in production. Fill the open phases of the lifecycle that governs how skills are designed, reviewed, and shipped, so non-engineers can build and ship intelligent automation end to end. • Build toward a connector-building agent: a meta-agent that discovers APIs, scaffolds MCP servers, and provisions access automatically. The end state is a platform that is itself an agent. • Work with our platform teams to establish the credential scoping, OpenTelemetry instrumentation, and least-privilege patterns that every connector and skill ships with, so security is built in from day one. • Own the employee experience for the agentic platform. Help onboard employees to the tools with self-serve guides, build skills people can learn from, and run the feedback loop between what's shipped and what adopters actually need. Your job isn't done when the connector ships. It's done when the team using it is self-sufficient. • Design credential scoping and vending for agent connectors: how API keys are provisioned, rotated, and scoped per user, per skill, per connector. OAuth/OIDC where it fits, least-privilege everywhere. • Build the risk-tier and review model for shared agent skills: what's safe at personal, team, and org level; sandboxing strategy; malicious dependency scanning for skills that pull in untrusted packages. • Instrument the agent platform end-to-end with OpenTelemetry: every MCP call, every skill execution, every credential use is visible in Coralogix.

🎯 Requisitos

• You've shipped production systems and can point to the seams: where they held under load, where they broke, and what you changed. Five or more years of that. • Proficient in at least one of Python, TypeScript/Node, or Rust. • You've built developer tooling, platforms, SDKs, or internal frameworks that other engineers depended on. You measure that work by adoption, not by what shipped. • You can build a real third-party integration: OAuth flows, credential scoping, webhook handling, pagination, rate limiting, retry semantics. Production connectors, not tutorial work. • Comfortable on AWS. We run on Lambda, API Gateway, DynamoDB, S3, and a managed agent runtime. You don't need to be an infra specialist, but you need to be at home. • You've made complex systems usable by non-experts, whether through DevX work or internal tools that non-engineers actually adopted and relied on. • You live and breathe AI tooling every day. Direct experience with Claude Code, MCP, or another agent framework (LangChain, CrewAI, AutoGen, OpenAI Agents SDK). • Familiarity with using different agent harnesses/orchestrators for complex coding tasks and the process of building new agents. • You've built production credential management: OAuth 2.0/OIDC, API key vending, secret rotation, least-privilege scoping. You understand that security that can be bypassed isn't security. • Strong AWS security fundamentals: IAM, KMS, Lambda surface, serverless attack patterns. You don't need to be a security specialist, but you ship code that doesn't need a security escort.

🏖️ Benefícios

• Competitive salary based on experience, with full medical and dental & vision benefits. • Stock in an early-stage startup growing quickly. • Generous, flexible paid time off policy. • 401(k) with Financial Guidance from Morgan Stanley.