Senior Machine Learning Platform Engineer — Model Hosting & MLOps
Core
Build infrastructure and engineering workflows to take custom ML models from development into reliable production use, focusing on GPU-backed LLM inference and real-time endpoints.
Role type
Senior IC machine learning platform engineer (MLOps & model hosting)
Builds
Secure, scalable inference services for custom models and agent workflows across AWS and Azure
Domain
Cloud infrastructure, MLOps, LLM serving
Deliverable
production ML models
Required skills
Python, Kubernetes, Terraform, AWS, Azure, GPU inference optimization, CI/CD pipelines, model lifecycle management, agent workflow orchestration, observability
Preferred skills
Advanced GPU inference tuning, hybrid/on-premises hosting, model registries, secure enterprise deployment patterns, self-service platform capabilities
Technologies
Kubernetes, AWS, Azure, Terraform, Python
Responsibilities
Design and build hosting for custom ML and AI models across AWS and Azure; Package models and dependencies into reproducible serving workloads; Provision and configure Kubernetes clusters; Develop infrastructure as code and deployment automation; Build MLOps workflows for model registration, versioning, and release; Partner with teams to design and prototype agent workflows; Establish production monitoring for service health and model behavior.
Seniority
Senior, hands-on IC