Description

You will lead technical implementation for AI and GPU workloads, deploying large language models and managing GPU infrastructure.

This role is on-site.

Responsibilities

• Deploy and configure LLMs using PyTorch and Hugging Face Transformers.
• Run GPU-based inference workloads utilizing NVIDIA CUDA.
• Set up and manage Linux-based environments, including shell scripting and package management.
• Manage GPU instances across cloud providers like AWS EC2 or GCP.
• Collaborate with the team to integrate models into production pipelines.

Required Skills

• 5+ years of professional experience in software engineering or ML operations.
• Expertise in Python, PyTorch, and Hugging Face Transformers.
• Mastery of Linux, specifically Ubuntu environments.
• Proficiency in shell scripting and package management.
• Hands-on experience deploying LLMs (Llama preferred).
• Experience running GPU-based inference using CUDA.
• Familiarity with cloud GPU platforms including AWS and Google Cloud Platform (GCP).
• Ability to create and maintain isolated Python environments using Conda and pip.

Key Skills

Education

Any Graduate