As a Senior AI Software Engineer in an AI Innovation organization within OCI, you will help build AI capabilities into Oracle products through strong software engineering, technical leadership, and high-quality execution.
Design, architect, and deliver scalable agentic AI systems capable of reasoning, planning, tool use, workflow execution, multi-step task orchestration, and safe human-in-the-loop escalation.
Serve as a technical owner for OCI AI platform capabilities, including agent execution, inference systems, model serving, AI workflow orchestration, evaluation, and observability.
Build production-grade services for tool calling, agent memory, context management, Model Context Protocol (MCP) integration, vector retrieval, multi-agent coordination, policy enforcement, and evaluation.
Develop distributed services optimized for low latency, high throughput, GPU efficiency, reliability, cost, operability, and secure multi-tenant operation.
Define service boundaries, APIs, data models, state management, consistency tradeoffs, failure modes, SLIs/SLOs, rollout strategies, and operational readiness criteria for AI platform services.
Integrate AI agents securely and reliably with enterprise APIs, cloud services, databases, identity systems, secrets management, and external systems.
Establish AgentOps and LLMOps practices for tracing, monitoring, eval suites, regression testing, experimentation, safety guardrails, prompt/tool versioning, and production reliability.
Evaluate and operationalize emerging technologies in generative AI, agentic workflows, inference optimization, long-context systems, reasoning models, AI developer tooling, and agentic-first development.
Drive engineering excellence through code reviews, design reviews, test strategy, deployment automation, incident analysis, documentation, and AI-assisted development practices using tools such as Codex, Claude Code, Cursor, Copilot, or similar systems.
Own critical production outcomes, including reliability, performance, security posture, cost efficiency, and supportability for the systems delivered.
Design, architect, and deliver scalable agentic AI systems capable of reasoning, planning, tool use, workflow execution, multi-step task orchestration, and safe human-in-the-loop escalation.
Serve as a technical owner for OCI AI platform capabilities, including agent execution, inference systems, model serving, AI workflow orchestration, evaluation, and observability.
Build production-grade services for tool calling, agent memory, context management, Model Context Protocol (MCP) integration, vector retrieval, multi-agent coordination, policy enforcement, and evaluation.
Develop distributed services optimized for low latency, high throughput, GPU efficiency, reliability, cost, operability, and secure multi-tenant operation.
Define service boundaries, APIs, data models, state management, consistency tradeoffs, failure modes, SLIs/SLOs, rollout strategies, and operational readiness criteria for AI platform services.
Integrate AI agents securely and reliably with enterprise APIs, cloud services, databases, identity systems, secrets management, and external systems.
Establish AgentOps and LLMOps practices for tracing, monitoring, eval suites, regression testing, experimentation, safety guardrails, prompt/tool versioning, and production reliability.
Evaluate and operationalize emerging technologies in generative AI, agentic workflows, inference optimization, long-context systems, reasoning models, AI developer tooling, and agentic-first development.
Drive engineering excellence through code reviews, design reviews, test strategy, deployment automation, incident analysis, documentation, and AI-assisted development practices using tools such as Codex, Claude Code, Cursor, Copilot, or similar systems.
Own critical production outcomes, including reliability, performance, security posture, cost efficiency, and supportability for the systems delivered.
