Staff ML Ops Engineer: Equity & Platform Lead

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

Benefits offered by this job

Health, dental, and vision coverage

401k with match

Flexible PTO

Job summary

LVT is seeking a Staff ML Ops Engineer to own the model lifecycle and platform driving production-ready AI workloads, including vision, LLM, and agentic workloads. You will craft standard self-serve tooling, model packaging, and versioned contracts for reliable deployments.

You will collaborate across AI/ML research, application backend, and platform teams, ensuring robust CI/CD, observability, and safe deployment practices while mentoring engineers toward scalable systems.

Qualifications

• 8+ years of engineering experience with deep ML-infrastructure / MLOps in production.
• Experience designing self-serve ML deployment, including model registry and CI/CD.
• Strong API design and observability focus across polyglot boundaries.

Responsibilities

• Own the model lifecycle end-to-end: packaging, CI/CD, versioned contracts, deployment and rollback, monitoring.
• Unify LLM, VLM, and vision workloads under one lifecycle with guardrails and cost/latency observability.
• Make the research-to-production path self-serve and safe by encoding security and on-call guardrails.
• Define and own the API boundary between the model platform and the application backend.
• Mentor IC productionization work toward the platform, setting technical standards.

Skills

MLOps & Platform Experience

LLMOps

Self-Serve ML Deployment

API Design

Technical Leadership

Education

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

Job description

LVT is seeking a Staff ML Ops Engineer to own the model lifecycle and platform driving production-ready AI workloads, including vision, LLM, and agentic workloads. You will craft standard self-serve tooling, model packaging, and versioned contracts for reliable deployments.

You will collaborate across AI/ML research, application backend, and platform teams, ensuring robust CI/CD, observability, and safe deployment practices while mentoring engineers toward scalable systems.