Machine Learning Engineer - LLM Systems & Research

As a Machine Learning Engineer, you will implement and maintain components of LLM inference systems under senior guidance, including model optimization and performance monitoring, deploying and configuring model serving solutions using established frameworks, and supporting optimization efforts for latency and throughput. You will contribute to ML pipeline development and maintenance, implement monitoring and evaluation components, and support research initiatives by implementing prototypes and helping translate research concepts into production-ready components. The technologies you will use include Python, Rust, SQL, YAML/JSON, PyTorch, Transformers, ONNX, TensorRT, Distributed training frameworks, Kubernetes, Docker, Cloud platforms (AWS/GCP/Azure), GPU clusters, PostgreSQL, Redis, Vector databases, S3/GCS, Data streaming (Kafka/Kinesis), Prometheus, Grafana, ELK stack, MLflow, and Weights & Biases.