Senior Machine Learning Engineer, Services/MLOps

What you'll do

• Own the full serving lifecycle for heterogeneous model pipelines from research checkpoints to enterprise endpoints.
• Deploy and scale model pipelines to meet specific enterprise latency and throughput budgets.
• Ensure served model quality matches training environments by closing gaps in precision and preprocessing.
• Engineer multi-tenant systems with data isolation to honor customer IP contracts and audit requirements.
• Build platforms for rapid pipeline deployment, observability, monitoring, and automated alerting.
• Define quality gates in deployment pipelines using automated evaluation, regression detection, and drift monitoring.
• Optimize GPU capacity and costs through efficient batching and right-sizing acceleration fleets.
• Manage production ML operations including on-call rotations, incident response, and postmortems.

What we're looking for

• Experience in machine learning engineering with ownership of production ML or inference services at scale.
• Master’s or PhD in Computer Science, Computer Engineering, or a related field, or equivalent practical experience.
• Strong Python and deep-learning engineering skills using PyTorch to deploy and scale model-backed services.
• Experience composing multi-model pipelines and serving them behind APIs with orchestration, batching, and autoscaling.
• Proven track record building observability, monitoring, and alerting for production services to meet latency and throughput targets.
• Experience with multi-tenant systems and data isolation in enterprise or regulated contexts.
• Fluency with containers and orchestration (Docker, Kubernetes), CI/CD for ML, and a major cloud provider (AWS or Azure).
• Experience with GPU inference optimization, including quantization and batching; custom CUDA is a plus (preferred).