GPU AI Inference Engineer | LLM Deployment & Optimization

Vyntrapro Innovations; Jakarta Pusat; On-site; IDR 70,000,000 - 110,000,000; Full time

Job summary

NVIDIA in Jakarta, Indonesia seeks an AI Software Engineer to build and optimize GPU-accelerated inference platforms. You will deploy and scale LLMs and GenAI apps, optimize latency, and drive performance across RTX, DGX, and cloud GPUs.

Ideal candidates bring 5+ years in AI software, extensive CUDA/TensorRT experience, and proficiency with PyTorch, Triton, and Kubernetes in distributed environments.

Qualifications

• 5+ years hands-on experience with NVIDIA AI software and GPU-accelerated inference stacks.

Responsibilities

• Build and optimize AI inference stacks on RTX, DGX, and cloud GPU platforms.
• Deploy and scale LLMs and GenAI applications.
• Optimize performance, latency, and GPU utilization.
• Work with modern AI frameworks and distributed AI infrastructure.

Skills

NVIDIA CUDA

NVIDIA NeMo & NIM

TensorRT / TensorRT-LLM

PyTorch

vLLM

Llama.cpp

Triton Inference Server

DGX & Multi-GPU Environments

Linux, Docker, Kubernetes

AI/LLM Inference Optimization

Education

5+ Years Experience

Tools

Docker

Kubernetes

Linux

Job description

NVIDIA in Jakarta, Indonesia seeks an AI Software Engineer to build and optimize GPU-accelerated inference platforms. You will deploy and scale LLMs and GenAI apps, optimize latency, and drive performance across RTX, DGX, and cloud GPUs.

Ideal candidates bring 5+ years in AI software, extensive CUDA/TensorRT experience, and proficiency with PyTorch, Triton, and Kubernetes in distributed environments.