About the position
At Oracle Cloud Infrastructure (OCI), we are building the future of cloud computing-designed for enterprises, engineered for performance, and optimized for AI at scale. We are a fast-paced, mission-driven team within one of the world's largest cloud platforms. The Generative AI Service team within OCI is focused on developing infrastructure and tools to operationalize Large Language Models (LLMs) and agentic AI systems. Our goal is to empower developers and enterprises to deploy intelligent applications and agents that integrate seamlessly with cloud services.
Responsibilities
- Contribute to the design and implementation of scalable, distributed systems that serve LLMs and support agent-based workflows.
- Work in a collaborative environment with applied scientists, ML engineers, and software teams to deliver performant and reliable AI infrastructure.
Requirements
- BS in Computer Science or related technical field.
- 6+ years of experience in backend software development with cloud infrastructure.
- Strong proficiency in at least one language such as Go, Java, Python, or C++.
- Experience building and maintaining distributed services in a production environment.
- Familiarity with Kubernetes, container orchestration, and CI/CD practices.
- Solid understanding of computer science fundamentals such as algorithms, operating systems, and networking.
Nice-to-haves
- MS in Computer Science.
- Experience working with LLM serving frameworks like vLLM, DeepSpeed, or FasterTransformer.
- Exposure to agent-based AI systems or tool-based inference workflows.
- Knowledge of cloud-native observability tools and scalable service design.
- Interest in compiler or systems-level software design is a plus.
Benefits
- Flexible medical, life insurance, and retirement options.
- Opportunities for community involvement through volunteer programs.
- Work-life balance support.
