Senior Application Software Engineer

Build secure, scalable AI platform capabilities for Oracle employees using Oracle Cloud Infrastructure (OCI). This Senior Application Software Engineer role is onsite in Nashville, TN and focuses on AI platform services that connect models, enterprise systems, and reusable workflows to improve productivity across Oracle.

What you will work on

You will design, develop, deliver, and maintain AI software solutions with an emphasis on secure delivery, scalable architecture, and real-world adoption. The role spans AI control plane and data plane services, integrations, backend services and APIs, and reusable AI workflows that support enterprise use cases.

• Develop AI control plane and data plane services, including Codex integrations, memory capabilities, and model routing components aligned to established architecture.
• Build reusable AI plugins, skills, GPT integrations, custom applications, backend services, and APIs for enterprise deployments.
• Use Codex and other AI development tools to accelerate implementation, testing, debugging, and documentation while maintaining engineering quality.
• Integrate AI models with enterprise applications, data sources, and workflows using runtime and middleware patterns that support interoperability and multi-tenant scale.
• Participate in architecture and code reviews; apply secure coding practices and follow standards for API versioning, compatibility, deprecation, and safe rollouts.
• Implement automated testing and AI evaluations to validate functionality, accuracy, security, reliability, and performance.
• Diagnose and resolve complex issues across models, plugins, backend services, and integrations, and translate feedback into product improvements.
• Implement logging, monitoring, usage telemetry, and observability; contribute to service-level objectives, capacity planning, resilience, and operational improvements.
• Develop AI cost and usage intelligence including cost attribution, forecasting, token budgets, threshold alerts, and reporting.
• Implement model selection and usage controls to balance cost, quality, risk, and performance, optimizing token consumption and context through caching, context management, and workload-specific routing.
• Create technical guidance, migration guides, and adoption playbooks to help teams adopt and maintain AI capabilities.

Qualifications

• Bachelor’s degree (e.g., B.Tech) in Computer Science/Engineering or a related field, plus at least 4 years of software development experience.
• 4+ years designing, developing, and delivering backend services, APIs, distributed systems, developer platforms, or cloud services.
• 4+ years programming in one or more: Java, Python, JavaScript, or Go.
• Experience developing and deploying on cloud platforms such as OCI, AWS, Azure, or Google Cloud.
• Experience with relational or NoSQL databases, including data modeling, querying, and backend integration.
• Experience with software design, API integration, automated testing, code reviews, debugging, and secure coding practices.
• Experience supporting production services through logging, monitoring, observability, incident resolution, reliability improvements, and performance optimization.
• Experience collaborating with engineering, architecture, security, product, and business stakeholders to deliver software capabilities.

Tools and technologies you may use

• OCI, AWS, Azure, Google Cloud
• Java, Python, JavaScript, Go
• Relational databases, NoSQL databases
• Codex, GPT, LLM
• Retrieval-augmented generation (RAG), Model Context Protocol (MCP)

Preferred skills

• Hands-on experience building, integrating, or operating AI-enabled applications, generative AI solutions, developer tools, or enterprise productivity applications.
• Experience using Codex or similar AI coding tools for development, testing, debugging, and documentation.
• Familiarity with LLM application patterns including prompt design, RAG, tool/function calling, agents, memory, evaluations, and model routing.
• Experience building AI plugins, skills, GPT integrations, reusable workflows, or shared AI services.
• Experience developing Model Context Protocol (MCP) servers and tools to connect AI applications and agents with enterprise APIs, backend services, and data sources, including authentication, authorization, testing, and observability.
• Knowledge of AI control plane and data plane concepts and integrating AI capabilities with backend services, APIs, and enterprise systems.
• Experience implementing AI security, privacy, model-access controls, and policy-based model selection.
• Experience with AI cost optimization including token and context management, usage telemetry, cost attribution, forecasting, budgeting, and caching.