Principal AI Platform Architect

Aimlroles; Seattle (WA); Remote; USD 168,000 - 230,000; Full time

Benefits offered by this job

Competitive base pay

Medical benefits

Discretionary incentive plan

Learning & development platform

Flexible work policy

Job summary

Serko is seeking a Principal Engineer to own the technical vision for our AI Platform and Operations. This remote role can be based in Washington or California, with responsibilities spanning model serving, feature stores, experiment tracking, and ML CI/CD.

You will mentor senior engineers, define long-term roadmap, optimize GPU compute and latency, and improve observability and reliability of AI workloads across production. A strong ML infrastructure background is required.

Qualifications

• 12+ years of engineering experience with at least 4 years at principal level.
• Deep expertise in ML infrastructure, model serving, and cloud ecosystems.
• Hands-on experience with LLM inference, distributed systems, and platform-scale tech.

Responsibilities

• Architect the long-term technical roadmap for the AI platform including model serving, feature stores, experiment tracking, and ML CI/CD.
• Set engineering benchmarks for deployment, versioning, A/B testing, and automated rollbacks.
• Lead GPU/compute efficiency and cost optimization while handling latency and throughput for LLMs at scale.
• Design advanced monitoring and alerting for AI workloads in production to improve observability.
• Drive platform reliability and collaborate with product teams to meet evolving needs.
• Mentor senior engineers and guide architecture reviews and evaluation of cloud services/ML frameworks.

Skills

Senior engineering

ML infrastructure

Python

Platform mindset

Mentoring

Tools

Triton

vLLM

Ray Serve

MLflow

Weights & Biases

Kubeflow

Docker

Helm

Job description

Serko is seeking a Principal Engineer to own the technical vision for our AI Platform and Operations. This remote role can be based in Washington or California, with responsibilities spanning model serving, feature stores, experiment tracking, and ML CI/CD.

You will mentor senior engineers, define long-term roadmap, optimize GPU compute and latency, and improve observability and reliability of AI workloads across production. A strong ML infrastructure background is required.