Generative AI Engineer

Position Overview:

We are seeking a talented Generative AI/LLM Engineer with a strong background in building and deploying AI models, focusing on leveraging state-of-the-art technologies like Azure OpenAI GPT-4, GPT-4 Vision, or GPT-4 Omni. Experience with Retrieval-Augmented Generation (RAG) and working with Vector Databases is essential. While fine-tuning large language models (LLMs) is a plus, it is not mandatory. A general understanding of how deep learning models are trained or fine-tuned is required. The ideal candidate should be able to quickly learn and implement advanced techniques, even if they do not initially possess all the required experience.

Key Responsibilities:

• Design, develop, and deploy generative AI models using GPT-4 variants, including GPT-4 Vision and GPT-4 Turbo, tailored to address specific business needs.
• Implement and optimize Retrieval-Augmented Generation (RAG) techniques for enhanced data-driven solutions.
• Build and manage AI services using Python frameworks such as LangChain or LlamaIndex, and develop APIs with FastAPI or Quart for efficient integration.
• Focus on scalability, performance, and optimization of AI solutions across cloud environments, particularly with Azure and AWS.
• Work with Vector Databases (mandatory) and optionally Graph Databases for enhanced data management.
• Utilize Cosmos DB and SQL for robust data storage and management solutions.
• Apply MLOps or LLMOps practices to automate and streamline the AI model lifecycle, including CI/CD pipelines, monitoring, and maintenance.
• Implement and manage Azure Pipelines for continuous integration and deployment.
• Continuously research and adopt the latest advancements in AI, with a focus on quick learning and implementation of emerging technologies.

Required Skills and Qualifications:

• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or a related field.
• A minimum of 1+ years of experience specifically in Generative AI/LLM technologies, and 5+ years of experience in related fields.
• Proficiency in Python and experience with frameworks like LangChain, LlamaIndex, FastAPI, or Quart.
• Expertise in Retrieval-Augmented Generation (RAG) and experience with Vector Databases (mandatory).
• Experience with Cosmos DB and SQL.
• Fine-tuning LLMs and experience with Graph Databases are good to have but not mandatory.
• Proven experience in MLOps, LLMOps, or DevOps with a strong understanding of CI/CD processes, automation, and pipeline management.
• Familiarity with containers, Docker, or Kubernetes is a plus.
• Familiarity with cloud platforms, particularly Azure or AWS, and experience with cloud-native AI services.
• Strong problem-solving abilities and a proactive approach to learning new AI trends and best practices quickly.