Description

Build and manage the infrastructure required to integrate Large Language Models into the platform.

This role is remote.

Responsibilities

• Design, develop, and deploy infrastructure for LLM integration.
• Translate AI Scientist requirements into scalable and secure platform components.
• Develop and maintain APIs and services for interaction between the platform and various LLMs.
• Implement monitoring and logging solutions for the LLM integration layer.

Required Skills

• 6 years of experience in platform engineering or related roles.
• Proficiency in Python, Java, JavaScript, or Go.
• Expertise in containerization using Docker and infrastructure orchestration tools.
• Strong understanding of distributed systems and microservices architecture.
• Experience with event-driven architecture using RabbitMQ.
• Experience with NoSQL and RDBMS.
• Experience building and working with APIs.
• Working knowledge of React.
• Experience with cloud platforms such as AWS, Azure, or GCP.

Preferred Skills

• Experience working with LLMs or deep learning models.
• Familiarity with DevOps principles and cloud security best practices.
• Experience with pipeline orchestration using Airflow or similar tools.

Key Skills

Education

Not specified