Senior MLOps Engineer — AI Observability

Luca Ferretti

Full-time · Senior · New_York

This role is no longer accepting applications

Similar open roles you can apply to now:

About the role

About the role: we are hiring a Senior MLOps Engineer to join the core platform team behind our AI observability product. Our customers run production LLM, forecasting, and recommendation workloads, and they rely on us for deployment standards, monitoring signals, and incident tooling that work under real operational pressure. This role is focused on infrastructure quality rather than experimentation. You will work across Kubernetes, AWS, and model operations workflows to improve reliability, standardise deployment patterns, and strengthen the systems our customers depend on. We are looking for someone who has already supported ML systems in production and who is comfortable designing for scale, failure, and long-term maintainability.

Responsibilities

Own the deployment and observability foundations used by customer-facing AI workloads across our platform
Build and improve drift detection, latency monitoring, and incident response tooling for model-serving systems
Standardise infrastructure patterns for new customer environments across AWS and Kubernetes
Partner with product and solutions engineering to turn recurring customer pain into platform capabilities
Mentor two mid-level platform engineers and raise the bar on design documentation

Requirements

6+ years in platform engineering, MLOps, or infrastructure with at least 2 years supporting ML systems in production
Kubernetes in production depth — multi-tenant clusters, autoscaling, workload isolation, and incident debugging
AWS at operational depth including EKS, IAM, CloudWatch, and VPC networking
MLflow or equivalent experiment tracking and model registry tooling in production settings
CI/CD ownership for infrastructure and deployment workflows
Python for internal tooling, automation, and debugging across the platform stack