LLMOps Engineer

Primary Responsibilities

• Design, develop, and deploy AI solutions leveraging cutting-edge tools, frameworks, and best practices.
• Fine-tune and deploy Large Language Models (LLMs) such as OpenAI and Azure-based services to deliver scalable AI applications.
• Implement and optimize Retrieval-Augmented Generation (RAG) architectures, leveraging vector databases for efficient data retrieval.
• Write clean, maintainable Python code following software development best practices, including GIT workflows, code reviews, and CI/CD pipelines.
• Collaborate with cross-functional teams to integrate AI solutions with existing data engineering pipelines and cloud infrastructure.
• Build and manage containerized AI applications using Docker and Kubernetes for scalability and reproducibility.
• Leverage Azure services for deploying, monitoring, and scaling AI applications in the cloud.

Required Qualifications

• Strong proficiency in Python programming with a deep understanding of the software development lifecycle.
• Expertise in working with LLMs, including fine-tuning, prompt engineering, and deployment.
• Hands-on experience with RAG architectures and vector databases for knowledge retrieval.
• Familiarity with SQL Server and/or Snowflake for data storage and retrieval.
• Proficiency in Docker for containerization and Kubernetes for orchestration of containerized applications.
• Solid understanding of Azure services for deploying and managing AI applications.

Preferred Qualifications

• Experience with advanced optimization techniques for LLMs in production.
• Exposure to managing and deploying large-scale AI systems in cloud environments.
• Knowledge of best practices in logging, monitoring, and debugging AI workflows.
• Ability to collaborate effectively with data engineering teams for seamless integration of AI pipelines.