Senior AI Platform Engineer: On-Prem & Cloud Leader

PEMCO; Seattle (WA); On-site; USD 155,000 - 189,000; Full time

Benefits offered by this job

401(k) matching

Paid time off

Holidays (8) + floating

Education assistance

Scholarship program

Flexible spending accounts

Job summary

PEMCO is seeking a Principal AI Platform Engineer to own PEMCO's AI platform, from GPU compute through model serving, retrieval, and governance. You will operate in a hands-on role with organizational influence and set the standards others build against.

You will lead the AI gateway, open-weight model serving, and the retrieval and orchestration layers, ensuring secure, controllable, and cost-efficient AI for PEMCO's insurance platforms.

Qualifications

• 6+ years in platform engineering, SRE, or technical operations at senior/lead scope.
• 2+ years running LLM/AI systems in production (or 4+ years ML platform operations).
• Hands-on open-weight model serving (vLLM, Triton/TensorRT-LLM or equivalent).
• LLM observability and evaluation experience (LangFuse, LangSmith, Arize).
• Experience building RAG systems: vector stores, embedding pipelines, document processing.
• FinOps/cost management for cloud consumption, ideally GPU or AI workloads.
• Working knowledge of AI security risks: prompt injection, data leakage, model abuse.

Responsibilities

• Own AI economics and observability, including telemetry for cost per agent, workflow, and outcomes.
• Run the AI gateway routing, quotas, and cost capture across providers and models.
• Stand up high-throughput open-weight serving with GPU capacity and quantization.
• Build the retrieval layer with vector stores and embedding pipelines.
• Operate production agents: deployment, monitoring, incident response, retirement.
• Shape architecture for reliability, security, and governance in AI solutions.
• Maintain governance RBAC for models and agents, participate in governance reviews.
• Manage compute/acceleration stack including Azure GPU VMs, AKS GPU pools, and on-prem options.
• Oversee model lifecycle from evaluation to retirement and optimize cost-to-capability.

Skills

Platform engineering

LLM systems

Open-weight serving

FinOps/cost management

Tools

vLLM

Triton/TensorRT-LLM

LangFuse

Job description

PEMCO is seeking a Principal AI Platform Engineer to own PEMCO's AI platform, from GPU compute through model serving, retrieval, and governance. You will operate in a hands-on role with organizational influence and set the standards others build against.

You will lead the AI gateway, open-weight model serving, and the retrieval and orchestration layers, ensuring secure, controllable, and cost-efficient AI for PEMCO's insurance platforms.