MLOps / AI Platform Engineer

About the Role

We're seeking an MLOps / AI Platform Engineer to join our partner companies bridging the gap between AI experiments and production systems. You'll build the infrastructure that lets AI teams ship models reliably: model serving pipelines, monitoring for drift and degradation, cost optimization, versioning, and automated evaluation. As companies move from AI prototypes to production workloads, this role ensures AI systems are as reliable and observable as any other critical infrastructure.

What You'll Do

• Build and maintain model serving infrastructure (batch and real-time)
• Implement monitoring for model performance, drift detection, and cost tracking
• Design CI/CD pipelines for model training, evaluation, and deployment
• Manage model versioning, experiment tracking, and reproducibility
• Optimize inference costs and latency across GPU/CPU workloads
• Collaborate with AI engineers on productionizing models and agents

Requirements

• 4+ years of DevOps/platform engineering, 2+ focused on ML workloads
• Experience with ML platforms (SageMaker, Vertex AI, MLflow, Weights & Biases)
• Strong containerization skills (Docker, Kubernetes) for model serving
• Proficiency with infrastructure as code (Terraform, Pulumi)
• Experience with GPU infrastructure and inference optimization
• Excellent English communication skills (B2+)

Nice to Have

• Experience with LLM serving frameworks (vLLM, TGI, Triton)
• Knowledge of feature stores (Feast, Tecton)
• Experience managing AI workload costs at scale ($10K+/month)
• Background in data engineering or traditional DevOps

Tech Stack

Benefits & Perks