AI LLM & GPU Infrastructure Engineer
Posted Updated
Description
ESYEN is seeking an AI LLM & Infrastructure Engineer to design, deploy, and operate AI and LLM infrastructure. You will work across GPU-based systems, cloud and on‑prem environments, collaborating with AI, software engineering, and R&D teams.
You will configure GPUs, VMs, storage, and networking for AI workloads, deploy open-source LLMs, and optimize performance. This role emphasizes reliability, scalability, and cost efficiency within an R&D setting.
Design and manage GPU infrastructure for AI/LLM workloads. Configure and maintain multi-GPU servers. Manage GPU, VRAM, storage, and compute resources. Support cloud, on-premise, and hybrid environments. Deploy and manage open-source LLMs. Configure inference servers using vLLM, SGLang, TGI. Optimize inference performance, latency, throughput, and resources. Support model quantisation and multi-GPU inference activities. Deploy AI workloads using Docker and Kubernetes. Support autoscaling, scheduling, and workload management. Configure networking and storage for AI workloads. Contribute to distributed and multi-node GPU environments. Monitor GPU, memory, inference performance, and system resources. Implement logging, monitoring, and observability. Investigate infrastructure bottlenecks and performance issues. Improve reliability, scalability, and infrastructure costs. Degree in CS/CE/EE is an advantage. Professional experience in AI infrastructure, system administration, cloud infra, or software engineering. Strong foundation in Linux-based devops and GPU/AI infrastructure is preferred. Health coverage Training opportunities Team activities Welfare benefits Flexible hours Career growthSkills
Sign in to read and join the discussion.