Software Engineer Graduate (Inference Infrastructure) - 2026 Start (PHD)
Summary
Build and optimize GPU-based AI inference infrastructure for large-scale LLM deployments, focusing on cluster management, security, and cost efficiency.
- Architect GPU and AI accelerator infrastructure
- Collaborate to deliver LLM inference solutions
- Design and build cluster management and orchestration systems
- Ensure ML platforms are secure and cost efficient
- Integrate open source and systems research into production systems
- Write production ready scalable maintainable code