Build, operate, and improve enterprise Generative AI platform capabilities for Developer Productivity and broader engineering use cases
Design and implement backend services, APIs, and integrations enabling secure and reliable use of LLMs across internal tools and workflows
Work with AI gateway technologies (Envoy AI Gateway, Kong AI Gateway, LiteLLM Proxy, or equivalents) for model routing, policy enforcement, observability, and cost control
Integrate GenAI systems with enterprise IAM platforms such as Microsoft Entra ID, including authentication, authorization, group-based access, service principals, and audit requirements
Build integrations with internal engineering systems, developer tools, enterprise data sources, and MCP servers/clients
Contribute to architecture and implementation decisions around MCP, including enterprise authorization patterns and Enterprise-Managed Authorization extension for MCP
Develop production-grade services using Python, TypeScript, or similar languages with focus on reliability, testing, observability, and maintainability
Contribute to CI/CD pipelines, infrastructure-as-code, cloud resources, Kubernetes workloads, and operational procedures for AI platform services
Evaluate GenAI frameworks, model providers, gateway technologies, and emerging standards; communicate trade-offs to technical and non-technical stakeholders
Create clear documentation for platform behavior, integration patterns, security assumptions, operational procedures, and known limitations
技術スタック
必須スキル
4+ years of professional software engineering experience building and operating production systems
Hands-on experience building backend services, APIs, platform services, or developer tools using Python, TypeScript, Java, Go, or similar languages
Experience deploying and operating production systems using cloud infrastructure, CI/CD, infrastructure as code, containers, and Kubernetes or equivalent orchestration platforms
Experience integrating applications or services with enterprise authentication and authorization systems (Microsoft Entra ID, OAuth2/OIDC, SAML, service principals, RBAC, or group-based access control)
Experience building systems that use LLM APIs or model providers (OpenAI, Azure OpenAI, Anthropic, Gemini, Vertex AI, Bedrock, or equivalent)
Understanding of production concerns for GenAI systems (access control, prompt handling, model routing, rate limits, observability, evaluation, cost management, data protection)
Ability to work across teams, ask clear questions, explain trade-offs, and turn ambiguous platform requirements into practical engineering plans
歓迎スキル（該当する場合）
Experience with AI gateway or LLM proxy technologies (Envoy AI Gateway, Kong AI Gateway, LiteLLM Proxy, OpenAI-compatible gateways, or equivalents)
Experience with Model Context Protocol (MCP) including MCP servers/clients, authorization patterns, tool permissions, and enterprise deployment trade-offs
Familiarity with emerging MCP standards such as the Enterprise-Managed Authorization extension
Experience building enterprise developer tools, platform engineering systems, internal tools, or secure self-service platforms
Experience with policy enforcement, audit logging, secrets management, identity-aware proxies, API gateways, or zero-trust architecture
Experience with retrieval-augmented generation, agentic workflows, or LLM evaluation frameworks
Experience with AWS infrastructure for AI, identity, networking, and platform services