Co-op Software Engineer - AI System & Infrastructure
Core
Design and build scalable, high-performance AI infrastructure platforms for LLM training and inferencing, optimizing cluster management, scheduling, and deployment.
Role type
Co-op Software Engineer (AI System & Infrastructure)
Builds
Scalable AI infrastructure platform for LLM training and inferencing
Domain
Cloud infrastructure, AI systems, distributed computing
Deliverable
production ML models
Required skills
Distributed system design, Cluster management, LLM model deployment, Elastic LLM, Container optimization, Kubernetes, vLLM, Ray, SGLang, TensorRT-LLM, PyTorch, Cuda, GPU technologies
Preferred skills
Nvidia TensorRT, Triton servers, Container virtualization, Serverless technologies, C/C++, Go, Java, Rust, Python, C#
Responsibilities
Identify scalability/performance issues in current LLM/multi-modal LLM systems, Initiate and charter innovation projects to build or re-architect AI infrastructure platform, Provide scalable and high-performance architecture design optimized for AI training and inferencing, Collaborate with internal and external teams to deliver project features improving system scalability and performance