Staff ML Ops Engineer

LiveView Technologies•Seattle, WA

22h•$213,300 - $272,000

About The Position

LVT is seeking a Staff ML Ops Engineer to own the model lifecycle as infrastructure, creating standardized self-serve tooling that takes models from research to production. The platform serves production computer-vision models and a growing set of LLM, VLM, and agentic workloads, bringing generative AI workloads under consistent lifecycle practices for serving, versioning, evaluation, guardrails, and cost and latency monitoring. This is a senior individual-contributor and technical-leadership role. The engineer will partner closely with AI/ML research, application backend, and platform and infrastructure teams, and will work across model-serving architectures, CI/CD and rollback design, polyglot service contracts, and production observability. Responsibilities include owning model and LLM operations, building safe self-serve deployment paths, defining the contract boundary with application backends, and setting technical standards while mentoring engineers. The beginning annual salary range is $213,300–$272,000, determined by location, job-related experience, and education or training. Total earning potential includes a bonus structure tied to meeting goals and employee equity. Full-time benefits include comprehensive health, dental, and vision coverage, retirement benefits with a 401(k) match of up to 4%, and flexible PTO. Applicants must be authorized to work in the U.S. Candidates must pass a drug screening and background check upon employment; some roles may also require a federal background check and fingerprinting.

Requirements

8+ years of engineering experience with deep ML-infrastructure or MLOps experience, including building and operating a production model deployment, serving, and monitoring platform.
Hands-on experience operating LLM or VLM workloads in production, including model serving or managed-provider integration, prompt and version management, generative evaluation, guardrails, and token cost and latency control.
Experience designing self-serve ML deployment for other teams, including model registry and packaging, model CI/CD, serving contracts, rollback, and drift or quality monitoring.
Strong systems and API design judgment across a polyglot boundary, with operational maturity to own security, observability, and on-call trade-offs.
Track record of setting technical direction and developing engineers through technical leadership; formal management experience is not required.
Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
Must be authorized to work in the U.S.
Must pass a drug screening and background check upon employment.

Nice To Haves

Computer vision or video model inference at scale, including GPU serving and latency and cost optimization.
Cloud-native infrastructure experience, such as Kubernetes, Argo, or a comparable deployment stack.
Experience standing up an ML platform from zero on a team that did not previously have one.
Experience deploying AI models to edge environments, such as NVIDIA Jetson or similar.
Experience with agentic and generative tooling, including LangGraph, MCP frameworks, vector databases, and inference or serving platforms.

Responsibilities

Own the end-to-end model lifecycle, including standardized packaging, model CI/CD, serving with stable versioned contracts, automated deployment and rollback, monitoring, and drift detection.
Bring LLM, VLM, and agentic workloads under the platform’s lifecycle practices, including version-pinned models and prompts, generative evaluation and regression suites, production guardrails, and token-level cost and latency observability.
Own operational seams for retrieval and agent orchestration, including vector stores and request tracing, where applicable.
Make the research-to-production path self-serve and safe by encoding security, observability, and on-call guardrails into deployment tooling.
Define and own the contract boundary between the model platform and application backend so engineers can integrate with deployed models independently.
Set technical standards and mentor individual contributors working on productionization and the platform.