Senior Machine Learning Engineer

Design, build, and scale serving infrastructure for LLMs and other machine learning models, ensuring high availability, performance, and computational efficiency. Implement and optimize end-to-end MLOps pipelines from training and fine-tuning to deployment and monitoring in production. Manage and optimize the use of specialized AI hardware to maximize throughput and minimize infrastructure costs.

Proficiency in Python, Java, or Go for backend service development in Machine Learning. Knowledge of MLOps or DevOps, and technologies such as Kubernetes, Docker, and Terraform. Familiarity with LLMs, transformer architectures, and serving technologies like vLLM, Triton, or SGLang, along with experience in cloud platforms like AWS, GCP, or Coreweave.