Description

You will manage Linux-based environments and deploy deep learning models on GPU-accelerated infrastructure.

This role is on-site.

Responsibilities

• Install and configure Large Language Models (LLMs) such as LLaMA.
• Run inference using NVIDIA CUDA on cloud-based GPU instances.
• Maintain Linux environments through shell scripting and package management.
• Manage dependencies and virtual environments using conda and pip.

Required Skills

• 5+ years of professional experience.
• Proficiency in Python.
• Hands-on experience with PyTorch and Hugging Face Transformers.
• Experience with Linux-based environments, specifically Ubuntu.
• Competency in shell scripting and package management.
• Familiarity with cloud GPU instances including AWS EC2, GCP, or Hugging Face Spaces.
• Experience running inference using NVIDIA CUDA.
• Knowledge of setting up virtual environments with conda or pip.

Preferred Skills

• Experience installing and configuring LLMs.

Key Skills

Education

Any Graduate