Join CallSupport, where we're transforming AI technology to make it accessible and actionable for businesses of all sizes. Our platform is revolutionizing the B2B landscape, enabling clients to build customized AI solutions with ease. We’re expanding our team and are looking for a talented DevOps Engineer with a specialization in MLOps and LLM Ops to contribute to our cutting-edge products.
Role Summary
As a DevOps Engineer focusing on MLOps and LLM Ops, you will ensure the scalability, reliability, and efficiency of the infrastructure powering our AI-driven speech and language models. You will collaborate closely with machine learning and engineering teams to streamline the deployment, monitoring, and maintenance of complex AI models, enhancing our platform's capabilities.
Key Responsibilities
- Develop and manage scalable, secure infrastructure for deploying TTS (Text-to-Speech), STT (Speech-to-Text), and LLM (Large Language Models) applications.
- Design and maintain CI/CD pipelines to automate the integration and deployment of AI models.
- Collaborate with ML engineers to optimize model training, validation, and deployment processes.
- Monitor and analyze system performance, troubleshoot issues, and implement solutions to maintain system reliability and efficiency.
- Apply best practices in cloud technology, containerization, and MLOps/LLM Ops to enhance operational workflows.
Who You Are
- Experienced Professional: You bring expertise in DevOps with a strong focus on MLOps and experience in LLM Ops.
- Cloud Expertise: Proficient in cloud platforms such as AWS, GCP, or Azure, particularly for ML and LLM environments.
- Containerization Guru: Skilled in container technologies like Docker and orchestration tools like Kubernetes.
- Collaborative Communicator: Capable of working effectively with technical and non-technical teams.
Minimum Qualifications