Tech Stack

Description

You will contribute to training foundation models for coding tasks, working on developing Large Language Models from scratch and deploying them into production. You'll collaborate with stakeholders to convert business requirements into technical specifications and train LLMs on a large GPU cluster.

Requirements

• Experience in design, deployment, and support of production ML systems
• Strong theoretical background in NLP and transformer-based approaches
• Proficiency with PyTorch and common NLP libraries
• Experience in distributed training of multi-billion parameter models
• Attention to detail and great communication skills

Responsibilities

• Convert business requirements into technical specifications
• Train LLMs from scratch on a large GPU cluster
• Collect and process pre-training and fine-tuning datasets
• Support and improve existing subsystems