Principal AI Platform Engineer

PEMCO

. Build and operate PEMCO’s AI platform, including GPU compute, model serving, retrieval, orchestration, observability, and governance .

Posted 9/23/2026full-timeSeattle • Washington • United StatesLead💰 $129,038 - $215,063 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and operating AI platforms, with a focus on GPU compute, model serving, and observability. Proficient in managing AI economics, security, and governance while optimizing model lifecycle and cost management.

Highest-signal resume keywords

AI Platform EngineeringOpen-Weight Model ServingLLM ObservabilityFinOps/Cost ManagementAI Security Risk Management

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

GPU ComputeModel ServingQuantizationRight-SizingRAG SystemsVector StoresEmbedding PipelinesDocument ProcessingMCP-Based OrchestrationToken Budgets

Tools & Technologies

VLLMTritonTensorRT-LLMLangFuseLangSmithArizeAzure GPU VMsAKS GPU Pools

Industry Keywords

AI GovernanceModel Lifecycle ManagementCloud ConsumptionRegulated Industry Experience

Tech Stack

Tools & technologies

AzureCloud

About the role

Key responsibilities & impact

Build and operate PEMCO’s AI platform, including GPU compute, model serving, retrieval, orchestration, observability, and governance
Own AI economics and observability through consumption telemetry, cost-per-agent/workflow/outcome metrics, token usage, GPU utilization, tracing, evaluation, and drift monitoring
Run a unified AI gateway for provider/model routing, fallback chains, quotas, and per-agent cost capture
Stand up high-throughput open-weight model serving on Azure GPU capacity using vLLM and Triton/TensorRT-LLM
Perform quantization and right-sizing, and produce sizing evidence for potential on-premise GPU investments
Build governed retrieval infrastructure with vector stores, embedding pipelines, chunking, and document processing
Deploy, monitor, support incidents for, and retire production agents using MCP-based orchestration and least-privilege identities
Represent platform reliability, security, and economics in AI solution reviews and propose architecture alternatives
Enforce AI governance through model/agent RBAC, prompt/output guardrails, and authority to block noncompliant deployments
Operate Azure GPU VMs and AKS GPU pools, with on-premise GPU build-out when justified
Manage model lifecycle from evaluation through retirement and optimize cost against capability through model selection, routing, caching, batching, and token budgets

Requirements

What you’ll need

Applicants must be a resident and work from Washington state, with occasional travel to headquarters in Seattle, Washington
6+ years in platform engineering, SRE, or technical operations at senior/lead scope
2+ years running LLM/AI systems in production, or 4+ years of ML platform operations
Hands-on open-weight model serving using vLLM, Triton/TensorRT-LLM, or equivalent
Experience with quantization and GPU right-sizing
LLM observability and evaluation experience with LangFuse, LangSmith, Arize class tools, or demonstrated ability to establish it
Experience building RAG systems, including vector stores, embedding pipelines, and document processing
FinOps/cost management for cloud consumption, ideally GPU or AI workloads
Working knowledge of AI security risks, including prompt injection, data leakage, and model abuse
Preferred: on-prem GPU infrastructure design, fine-tuning/LoRA, agent frameworks (MCP, LangChain/LangGraph, Semantic Kernel), and regulated-industry experience

Benefits

Comp & perks

Medical, dental, and vision plans for employees and eligible family members with generous employer premium cost shares
Employer-paid basic life and accidental death & dismemberment insurance
Long- and short-term disability benefits
401(k) plan with a generous employer match (2 for 1 on the first 6% employee pre-tax and/or Roth deferral, up to federal maximums)
Vacation and eight paid holidays
Four floating holidays
Up to ten days of sick leave immediately upon hire, pro-rated based on hire date and full-time/part-time status
Paid time off for bereavement, jury duty, and employee volunteering
Education Assistance Program after one year of service
Scholarship program for children of PEMCO employees after one year of service
Children’s birthday gift program
Flexible Spending Accounts
Employee Assistance Program
Charitable gift matching
Discretionary bonuses
Tiered sales commissions and/or incentives