Staff ML Ops Engineer | End-to-End ML Platform, Equity

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

Benefits offered by this job

401k match

Flexible PTO

Health coverage

Job summary

LVT is seeking a Staff ML Ops Engineer to own the model lifecycle and build a self-serve platform that unifies vision models, LLMs, VLMs, and agentic workloads. You will collaborate with AI/ML research, the application backend team, and platform groups to design scalable serving, versioning, guardrails, and observability.

You will lead technical standards, mentor engineers, and shape how we ship models from research to production.

Qualifications

• 8+ years of engineering experience with ML infrastructure/MLOps.
• Experience deploying ML models including LLM/VLM workloads.
• Experience designing self-serve ML deployment with model registry and CI/CD.
• Strong API design and security/observability mindset.

Responsibilities

• MLOps: end-to-end model lifecycle, packaging, a model CI/CD path, a serving layer with stable, versioned contracts, automated deployment and rollback, and monitoring and drift detection.
• LLMOps: manage LLM/VLM workloads with prompts versioned as deployable artifacts; guardrails, evaluation, and latency cost observability; manage vector stores and tracing for retrieval or orchestration.
• CI/CD: enable research-to-production self-serve with security/observability guardrails.
• API Boundary Ownership: define and own the contract boundary between model platform and app backend.
• Technical Mentorship: set technical standards and mentor IC productionization work toward the platform.

Skills

MLOps

Platform Engineering

LLMOps

Self-Serve ML Deployment

API Design

Technical Leadership

Education

Bachelor's or Master's in Computer Science or Engineering

Tools

Kubernetes

Argo

Vector Databases

Model Serving

CI/CD for ML

Job description

LVT is seeking a Staff ML Ops Engineer to own the model lifecycle and build a self-serve platform that unifies vision models, LLMs, VLMs, and agentic workloads. You will collaborate with AI/ML research, the application backend team, and platform groups to design scalable serving, versioning, guardrails, and observability.

You will lead technical standards, mentor engineers, and shape how we ship models from research to production.