Lead AI Platform & ML Ops Architect - Remote

Serko; Seattle (WA); On-site; USD 168,000 - 230,000; Full time

Job summary

Serko is seeking a Principal Engineer to serve as the technical expert for our AI Platform & Operations. This role owns the technical vision for the foundational systems that power AI product teams across the company.

Remote Role - can be based in either Washington or California State. You’ll build robust, self-serve internal developer platforms enabling engineers to deploy, monitor, and scale AI models with efficiency and safety, ensuring a reliable and cost-effective future.

Qualifications

• 12+ years of engineering experience, with at least 4 years at a Principal or Distinguished level.
• ML infrastructure mastery with model serving and cloud ecosystem experience.
• Proficiency in Python and systems thinking for containerization (Docker/Helm).
• Experience building internal platforms that accelerate engineering velocity.

Responsibilities

• Architect the long-term technical roadmap for the AI platform (model serving, feature stores, experiment tracking, CI/CD for ML).
• Set engineering benchmarks for deployment, versioning, A/B testing, and automated rollbacks.
• Lead GPU/compute optimization and manage LLM inference at scale (quantization, batching, latency).
• Design advanced observability, monitoring, and alerting for AI workloads in production.
• Champion reliability, platform stability, and collaboration with product teams.
• Mentor senior engineers, lead architecture reviews, evaluate cloud services and ML frameworks.

Skills

Senior Engineer

ML Infrastructure

Python Proficiency

LLM Inference

Platform Thinking

Leadership & Mentoring

Tools

Kubernetes

Docker

Helm

Kubeflow

MLflow

Weights & Biases

Job description

Serko is seeking a Principal Engineer to serve as the technical expert for our AI Platform & Operations. This role owns the technical vision for the foundational systems that power AI product teams across the company.

Remote Role - can be based in either Washington or California State. You’ll build robust, self-serve internal developer platforms enabling engineers to deploy, monitor, and scale AI models with efficiency and safety, ensuring a reliable and cost-effective future.