MLOps Engineer

Sourced from jobs-in.us

This MLOps Engineer role focuses on designing, building, and operating high-performance inference platforms for deploying large machine learning models, including LLMs, into production environments. The position emphasizes optimizing system performance through advanced techniques like request routing, dynamic batching, caching, and autoscaling to maximize GPU utilization. Candidates will be responsible for ensuring scalable and efficient model serving infrastructure.

• Design and build high-performance inference platforms for production ML models
• Optimize request routing, dynamic batching, and caching strategies
• Implement autoscaling mechanisms to maximize GPU utilization
• Maintain and operate scalable model serving infrastructure

• Experience designing and operating ML inference platforms
• Strong understanding of LLM deployment and optimization techniques
• Proficiency in cloud infrastructure and containerization
• Knowledge of GPU resource management and performance tuning

• Familiarity with distributed training frameworks
• Experience with Kubernetes and service mesh technologies