Software Developer 4

Oracle Oracle · Enterprise · Seattle, WA +1

Software Developer 4 role focused on building backend services and APIs for AI-native applications and hosted agents. The role involves designing and implementing integrations for agent runtimes, tool execution, guardrails, and enterprise workflow automation within Oracle's OCI production environments. Key responsibilities include developing secure patterns, partnering with product teams to create agentic solutions, and improving the reliability and scalability of AI services.

What you'd actually do

  1. Design and implement backend services and APIs for AI-native applications, hosted agents, and enterprise workflow automation.
  2. Build integrations across agent runtimes, MCP servers, tools gateway, identity systems, guardrails, and Oracle service APIs.
  3. Develop secure patterns for tool execution, policy checks, human approval flows, audit traces, and action validation.
  4. Partner with AI Services, Data Platform, Console AI, Support, Retail, Fusion, and other product teams to convert business workflows into production-ready agentic solutions.
  5. Improve reliability, scalability, observability, and operational readiness for AI solutions running in OCI production environments.

Skills

Required

  • backend services and APIs
  • AI-native applications
  • hosted agents
  • enterprise workflow automation
  • integrations
  • agent runtimes
  • MCP servers
  • tools gateway
  • identity systems
  • guardrails
  • Oracle service APIs
  • secure patterns for tool execution
  • policy checks
  • human approval flows
  • audit traces
  • action validation
  • distributed systems
  • cloud services
  • APIs
  • production operations
  • secure service integrations
  • identity
  • authorization
  • auditability
  • policy enforcement
  • OCI
  • Kubernetes/containers
  • Java/Python/TypeScript
  • service telemetry
  • operational excellence
  • working across teams
  • shaping reusable platform capabilities

Nice to have

  • LLMs
  • AI agents
  • RAG
  • tool calling
  • MCP
  • hosted tools
  • vector stores
  • agent orchestration patterns
  • ambiguous product goals
  • concrete technical designs
  • reliable implementation plans

What the JD emphasized

  • AI solution designs
  • agents to plan, reason, call tools, access enterprise systems, execute workflows
  • AI Apps Gateway
  • Agent / MCP Gateway integrations
  • hosted agent workflows
  • tool discovery and execution
  • structured outputs
  • guardrails
  • approval flows
  • grounding
  • evaluation traces
  • reusable MCP patterns
  • backend services and APIs for AI-native applications, hosted agents, and enterprise workflow automation
  • integrations across agent runtimes, MCP servers, tools gateway, identity systems, guardrails, and Oracle service APIs
  • secure patterns for tool execution, policy checks, human approval flows, audit traces, and action validation
  • production-ready agentic solutions
  • modernize existing AI services using Agent One, MCP enablement, reusable tools, and shared platform capabilities
  • reliability, scalability, observability, and operational readiness for AI solutions running in OCI production environments
  • service contracts, schemas, SDK/API patterns, onboarding templates, and repeatable engineering standards
  • customer-facing and internal AI initiatives such as Console AI, AI service modernization, agentic document/language workflows, AI solutioning, and MCP-based enterprise integrations
  • agent runtimes
  • MCP servers
  • tools gateway
  • identity systems
  • guardrails
  • Oracle service APIs
  • tool execution
  • policy checks
  • human approval flows
  • audit traces
  • action validation
  • AI Services
  • Data Platform
  • Console AI
  • Support
  • Retail
  • Fusion
  • business workflows
  • production-ready agentic solutions
  • Agent One
  • MCP enablement
  • reusable tools
  • shared platform capabilities
  • reliability
  • scalability
  • observability
  • operational readiness
  • AI solutions
  • OCI production environments
  • architects
  • senior engineers
  • service contracts
  • schemas
  • SDK/API patterns
  • onboarding templates
  • repeatable engineering standards
  • customer-facing and internal AI initiatives
  • Console AI
  • AI service modernization
  • agentic document/language workflows
  • AI solutioning
  • MCP-based enterprise integrations
  • backend engineering experience
  • distributed systems
  • cloud services
  • APIs
  • production operations
  • secure service integrations
  • identity
  • authorization
  • auditability
  • policy enforcement
  • LLMs
  • AI agents
  • RAG
  • tool calling
  • MCP
  • hosted tools
  • vector stores
  • agent orchestration patterns
  • ambiguous product goals
  • concrete technical designs
  • reliable implementation plans
  • OCI
  • Kubernetes/containers
  • Java/Python/TypeScript
  • service telemetry
  • operational excellence
  • working across teams
  • shaping reusable platform capabilities
  • one-off feature implementations

Other signals

  • AI solution designs
  • agents to plan, reason, call tools, access enterprise systems, execute workflows
  • platform components such as AI Apps Gateway, Agent / MCP Gateway integrations, hosted agent workflows, tool discovery and execution, structured outputs, guardrails, approval flows, grounding, evaluation traces
  • backend services and APIs for AI-native applications, hosted agents, and enterprise workflow automation
  • integrations across agent runtimes, MCP servers, tools gateway, identity systems, guardrails, and Oracle service APIs
  • secure patterns for tool execution, policy checks, human approval flows, audit traces, and action validation
  • convert business workflows into production-ready agentic solutions
  • modernize existing AI services using Agent One, MCP enablement, reusable tools, and shared platform capabilities
  • Improve reliability, scalability, observability, and operational readiness for AI solutions running in OCI production environments
  • define service contracts, schemas, SDK/API patterns, onboarding templates, and repeatable engineering standards
  • Support customer-facing and internal AI initiatives such as Console AI, AI service modernization, agentic document/language workflows, AI solutioning, and MCP-based enterprise integrations