Software Engineer - LLM Inference

Nutanix is seeking a Software Engineer to join the LLM Inference team, focusing on architecting and developing scalable, containerized services on Kubernetes. The role involves optimizing low-level systems for low-latency, high-throughput performance and contributing to open-source cloud native projects.

• Architect, design, and develop horizontally scalable, containerized, fault-tolerant services on Kubernetes.
• Improve system performance for low-latency and high-throughput use cases.
• Optimize any part of the stack, including low-level systems.
• Develop scalable observability architectures for metrics collection and analysis.
• Collaborate with globally distributed product and backend teams.

• 2-5 years experience in product development with maintainable code.
• Strong programming fundamentals, data structures, and algorithms.
• Strong experience with Docker, Kubernetes, and cloud native technologies.
• Experience building applications with Go and Python.
• Experience building and managing CI/CD pipelines.
• Understanding of datacenter design, distributed computing, and OS internals.

• Familiarity with ML frameworks (TensorFlow, PyTorch).