Senior MLOps Engineer

What this role involves

Nace AI is hiring a Senior MLOps Engineer to own the infrastructure for training, serving, and evaluating specialized Small Language Models (SLMs) in production. The role involves designing and operating pipelines, orchestration, and serving layers, with a focus on reliability for enterprise audit and finance workflows. The position is based in Palo Alto, CA, and requires on-site presence.

Skills this posting asks for

• mlops
• ml infrastructure
• platform engineering
• llm inference
• vllm
• sglang
• tgi
• trt
• kubernetes
• docker
• terraform
• gpu cluster management
• distributed training
• python
• airflow
• kubeflow
• ray
• mlflow
• weights & biases
• aws
• gcp
• azure
• quantization
• awq

Requirements

• 5 years of experience
• Level: senior
• Remote policy: onsite

From the employer’s posting

Palo Alto, CA | Full-Time | On-site About Nace AI: Nace AI is an enterprise AI product and research company in Palo Alto (backed by General Catalyst, Walden Catalyst, and Intel). We build long-running AI agents powered by our own specialized SLMs — we started with financial audit and accounting w…