Job Description
We are looking for a skilled MLOps Engineer to join our dynamic team, focusing on deploying, managing, and optimising Large Language Models (LLMs) across various platforms. The ideal candidate will have a strong background in MLOps, with experience in deploying models on multiple GPUs, scaling, load balancing, and managing data pipelines. This role is critical in ensuring the high performance and reliability of our AI-driven solutions.
Responsibilities:
* Deploy LLMs using platforms like Huggingface, Sagemaker, or similar.
* Manage deployment on multiple GPUs, ensuring optimal performance.
* Implement scaling and load balancing to handle varying loads efficiently.
* Design and maintain data pipelines for model training, preferably using Kubeflow.
* Establish continuous integration and delivery pipelines using Docker, Kubernetes, or AWS counterparts (e.g., ECR).
* Visualise fine-grained MLOps data using industry standard tools and platforms
* Ensure system security through triaging, log analysis, and infrastructure debugging.
* Implement Infrastructure as Code using tools like Terraform or CloudFormation.
Requirements:
* Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field or equivalent experience.
* Solid experience with MLOps practices, deploying on multiple GPUs, and managing scalable systems.
* Proficiency in Kubeflow, Docker, Kubernetes, and AWS services.
* Experience with LangChain, prompt engineering, and fine-tuning LLMs is highly desirable.
* Strong background in data visualisation, and ES+Kibana.
* Knowledge in security practices, including log analysis and infrastructure debugging.
* Familiarity with Infrastructure as Code (Terraform, or CloudFormation).
* Excellent problem-solving skills and ability to work in a fast-paced environment.
Preferred Qualifications:
* Experience with visualisation tools and techniques for AI model insights.
* AWS certification with a focus on security and scalability.
* Proven track record in deploying and managing AI models in production environments.
The ideal candidate is proactive, frequently questions things to ensure clarity and understanding, communicates clearly and effectively with all team members, and has experience working in an early-stage company environment
#J-18808-Ljbffr