MLOps / AI Infrastructure Engineer

Helix Systems is scaling its AI platform to serve enterprise customers globally. We need an MLOps engineer who can build the infrastructure that keeps our AI systems running reliably at scale.

This is not a research or model-building role. It's about making sure the systems that serve predictions, run agents, and process data are fast, reliable, and observable.

What you'll own: - LLM serving infrastructure (vLLM, TGI) on AWS - ML pipeline orchestration with Airflow and Prefect - Model monitoring, drift detection, and evaluation at scale - Cost optimization for LLM API usage across the platform

Requirements: - 3+ years in MLOps or AI infrastructure roles - Experience with LLM serving frameworks (vLLM, TGI, BentoML) - Strong AWS or GCP skills - Python and infrastructure-as-code (Terraform or CDK)