Principal Application Software Engineer

Oracle Oracle · Enterprise · Nashville, TN +1

This Principal Application Software Engineer role on the Oracle Cloud Infrastructure (OCI) AI Platform and Productivity Engineering team focuses on designing and operating the AI control and data planes. The role involves managing aspects like Codex enablement, plugin strategy, memory, model routing, and AI cost/usage intelligence. Key responsibilities include developing scalable software solutions, defining enterprise technical guidance for AI applications, and ensuring secure, compliant, and reliable AI delivery. The role emphasizes LLM application patterns, AI governance, and cost optimization, aiming to enable safe and efficient AI scaling for enterprise use.

What you'd actually do

  1. Designs, delivers, and operates scalable, secure software solutions by leading requirements analysis, architecture and code reviews, API integration and lifecycle strategy, complex debugging and performance optimization, and comprehensive testing, logging, monitoring, and observability practices.
  2. Design and development for control-plane/data-plane architecture, Codex architecture, model routing,
  3. Define enterprise technical guidance for plugin, Skill, GPT, custom application.
  4. Leads cross-team evolution of middleware and runtime standards, defining safe versioning, deprecation, and rollout practices while driving shared observability, SLO, and resilience patterns.
  5. Develops scalable software, systems, and services; recommends project and design scope; applies architectural standards and performance optimization; and coaches engineers while collaborating with stakeholders to align solutions with the broader technical architecture.

Skills

Required

  • 7 years of experience in software development
  • 5+ years of experience designing and delivering scalable distributed systems, APIs, developer platforms, or cloud services.
  • 3+ years of experience with cloud platforms such as OCI, AWS, Azure, or Google Cloud.
  • 3+ years of experience with programming languages such as Java, Python, JavaScript, Go
  • Experience with production operations, including observability, logging, monitoring, incident response, service reliability, and performance optimization.
  • Experience working across engineering, architecture, security, product, and business stakeholders to deliver shared platform capabilities.
  • 4 years of experience with databases.

Nice to have

  • Experience building, integrating, or operating AI-enabled applications, generative AI platforms, developer tools, or enterprise productivity solutions.
  • Experience with LLM application patterns, including prompt design, retrieval-augmented generation, tool/function calling, agents, memory, evaluations, and model routing.
  • Experience designing AI control-plane/data-plane architecture, reusable plugins, Skills, GPTs, shared services, or enterprise AI enablement platforms.
  • Experience implementing AI governance, security, privacy, model-access controls, policy-driven model selection, or certification processes.
  • Experience with AI cost optimization, including token and context management, usage telemetry, cost attribution, forecasting, budgeting, caching, and model-performance optimization.
  • Experience defining API standards, versioning, deprecation, rollout, and interoperability strategies for platforms with multiple downstream consumers

What the JD emphasized

  • AI Platform and Productivity Engineering
  • AI cost, token, and usage intelligence
  • dynamic model enforcement
  • LLM application patterns
  • prompt design
  • retrieval-augmented generation
  • tool/function calling
  • agents
  • memory
  • evaluations
  • model routing
  • AI governance
  • security
  • privacy
  • model-access controls
  • policy-driven model selection
  • certification processes
  • AI cost optimization
  • token and context management
  • usage telemetry
  • cost attribution
  • forecasting
  • budgeting
  • caching
  • model-performance optimization
  • API standards
  • versioning
  • deprecation
  • rollout
  • interoperability strategies

Other signals

  • AI Platform and Productivity Engineering
  • AI cost, token, and usage intelligence
  • dynamic model enforcement
  • LLM application patterns