Staff ML Ops Engineer — Self-Serve Platform

LiveView Technologies; Seattle (WA); On-site; USD 213,000 - 272,000; Full time

Benefits offered by this job

Health, dental, vision coverage

401k match up to 4%

Flexible PTO

Job summary

LiveView Technologies is seeking a Staff ML Ops Engineer to own the model lifecycle and infrastructure, turning research into production-ready, self-serve tooling. You’ll oversee ML and AI workloads across vision models, LLMs, and agentic tasks, ensuring stable deployment, versioning, guardrails, and observability.

You will collaborate with AI/ML research, backend, and platform teams, discuss model-serving architectures, CI/CD, and production observability, while mentoring others toward scalable

Qualifications

• 8+ years of engineering experience with deep ML-infrastructure / MLOps work.
• Hands-on experience operating LLM or VLM workloads in production.
• Experience designing self-serve ML deployment for other teams, including model registry and packaging, CI/CD for models, serving contracts, rollback, and drift monitoring.
• Strong systems and API design judgment across a polyglot boundary.
• Track record of setting technical direction and mentoring engineers toward platform goals.

Responsibilities

• Own the model lifecycle end to end: packaging, CI/CD, serving layer, versioned contracts, deployment and rollback, monitoring and drift detection.
• Unify LLM/VLM workloads with vision models under a single platform discipline, with guardrails and cost/latency controls.
• Encode security, observability, and on-call guardrails to enable self-serve, safe production for model owners.
• Define and own the contract boundary between the model platform and application backend.

Skills

MLOps & Platform

LLMOps

Self-Serve ML Deployment

API Design

Technical Leadership

Education

Education

Bachelor's or Master's in CS/Engineering or related

Equivalent practical experience

Tools

Kubernetes

Argo

LangGraph

Vector databases

MLOps tooling

Job description

LiveView Technologies is seeking a Staff ML Ops Engineer to own the model lifecycle and infrastructure, turning research into production-ready, self-serve tooling. You’ll oversee ML and AI workloads across vision models, LLMs, and agentic tasks, ensuring stable deployment, versioning, guardrails, and observability.

You will collaborate with AI/ML research, backend, and platform teams, discuss model-serving architectures, CI/CD, and production observability, while mentoring others toward scalable