AI Senior Staff Systems Engineer
Core
Lead the end-to-end lifecycle of AI infrastructure, including architecting GPU clusters, deploying LLMs, and managing agentic AI workflows.
Role type
Senior Staff AI Systems Engineer (Infrastructure & Deployment)
Builds
High-performance GPU clusters, LLM serving platforms, and agentic AI services
Domain
AI Infrastructure, High-Performance Computing, Cloud AI Services
Deliverable
production ML models
Required skills
NVIDIA GPU architecture (CUDA, cuDNN), Linux system administration, Docker & Kubernetes, Python/Bash scripting, LLM deployment & optimization, CI/CD pipelines, cloud AI service management (Azure, GCP)
Preferred skills
LSF cluster administration, AI job profiling & tuning, macOS/AppleSilicon system administration
Technologies
PyTorch, TensorFlow, vLLM, TGI, TensorRT-LLM, LSF, Docker, Kubernetes, Azure OpenAI, Google Cloud Platform, CUDA, cuDNN
Responsibilities
Design and implement next-generation AI infrastructure and GPU clusters; Deploy, serve, and optimize Large Language Models (LLMs); Manage public cloud AI services (Azure, GCP) including access and billing; Configure and optimize GPU server clusters and job schedulers; Architect and deploy scalable AI tech stacks and CI/CD pipelines; Develop automation scripts and monitoring solutions; Mentor engineers on AI systems best practices.
Seniority
Senior Staff, hands-on IC with mentorship responsibilities