Das ist der Job
Your work ensures that models are deployed safely, monitored continuously, and optimized for performance at scale.
Darum lohnt es sich
MLOps Engineer at LockedIn AI, Remote (United States) As an MLOps Engineer at LockedIn AI, you will design and manage the infrastructure that powers ML models from development to production. You will build robust pipelines, automate ML workflows, and ensure system reliability for latency-sensitive AI applications serving millions of users.
Key Responsibilities ML Lifecycle Ownership Manage end-to-end model deployment for LLMs, RAG systems, and speech models Build scalable inference infrastructure with low latency and high availability Implement versioning, model registries, and deployment strategies (A/B, canary, rollback) ML Pipeline Automation Design CI/CD pipelines for training, testing, validation, and deployment Automate retraining workflows triggered by drift or data updates Ensure ML workflows are fully reproducible and test-driven Monitoring & Reliability Build real-time monitoring systems for model performance and latency Detect data drift and performance degradation early Set up alerting systems and dashboards for operational visibility Infrastructure & Scaling Manage GPU-based compute environments and cloud infrastructure Optimize inference cost, storage, and token usage Use Docker and Kubernetes for scalable ML workloads Data & Feature Systems Build data pipelines for training and validation workflows Implement data versioning and lineage tracking Col
