Overview

As a Senior Software Engineer (IC3) at Oracle, you will develop and maintain components of our LLM-serving and agentic AI infrastructure. Collaborate with senior engineers to build scalable services, automate deployments, and ensure operational excellence in production. This hands-on role is ideal for engineers passionate about distributed systems and AI infrastructure.

Responsibilities

• Design and implement scalable microservices for LLM inference and agent orchestration.
• Develop and optimize high-throughput APIs for AI model serving.
• Automate CI/CD pipelines and infrastructure deployment using Kubernetes and Terraform.
• Monitor and troubleshoot production systems for reliability and performance.
• Build observability tooling with metrics, logging, and tracing integration.
• Collaborate on system architecture for distributed AI workloads.
• Optimize resource utilization and cost efficiency in cloud environments.
• Contribute to open-source projects and internal tooling for AI infrastructure.

Qualifications

• 5+ years of experience in software development with distributed systems.
• Strong proficiency in Go, Python, or Java for backend services.
• Experience with Kubernetes, Docker, and cloud platforms (OCI, AWS, GCP).
• Knowledge of AI/ML infrastructure, model serving, or inference optimization.
• Expertise in observability tools (Prometheus, Grafana, ELK stack).
• Bachelor's degree in Computer Science or equivalent experience.

Benefits

• Competitive salary and equity in Oracle's growth.
• Comprehensive health, dental, and vision insurance.
• 401(k) matching and employee stock purchase plan.
• Flexible PTO and remote/hybrid work options.
• Professional development budget and conference sponsorships.