Senior MLOps Engineer

Requirements:
6+ years of hands-on experience building, deploying, and operating ML pipelines and distributed model-serving systems at scale.
Production experience with model lifecycle management including dataset management, training, experimentation, versioning, deployment, and monitoring using tools like MLflow, Weights & Biases, SageMaker or similar.
Strong background in model optimization and inference acceleration for NLP/Vision models (e.g., vLLM, ONNX Runtime, TensorRT, quantization, and distillation).
Proven ability to refactor research code into production-ready services with automated testing and continuous integration (CI/CD).
Proficiency in Python and infrastructure-as-code (Terraform, CloudFormation, or similar).
Hands-on experience with Kubernetes-based deployments, Kubeflow, Ray or similar for scalable model serving.
Experience with cloud-native ML services (AWS SageMaker, GCP Vertex AI, or Azure ML).
Knowledge of stream and batch processing frameworks (Kafka, Flink, Spark Structured Streaming) is an advantage.
Experience with dataset management and data generation
Strong communication, ownership, and problem-solving mindset.