Staff AI Platform Engineer: Scale ML Infra

DAT Freight Solutions; Seattle (WA); Hybrid; USD 198,000 - 246,000; Full time

Benefits offered by this job

Medical Insurance

Dental Insurance

Vision Insurance

Life Insurance

AD&D Insurance

401k matching

Employee Stock Purchase Plan

Paid time off

Transit benefits

Job summary

DAT Freight & Analytics is seeking a Staff AI Platform Engineer to own the platform for all AI/ML workloads. You will set architectural direction for model gateway, inference, feature storage, and observability across the organization.

You will lead AI system architecture, drive alignment with Product and Engineering, and build scalable, production-grade infrastructure on AWS. This role emphasizes mentorship and incident management while delivering high-impact ML platforms.

Qualifications

• 10+ years of software engineering experience with production infrastructure ownership.
• 4+ years building and operating ML/AI platforms end-to-end.
• Strong development skills in TS/Node.js, Java, or Go; ability to ship reusable libraries.
• Extensive AWS experience with production systems including EKS, Lambda, S3, and managed services.
• Hands-on experience deploying models at scale: GPU scheduling, batching, and real-time vs batch tradeoffs.
• Practical experience with LLM systems in production and vector databases.
• Proven experience building evaluation/monitoring for models; defining regression criteria.
• Experience mentoring engineers and data scientists; raising the operational bar.

Responsibilities

• Platform Ownership: Design, build, and operate shared services for models including a model gateway and inference endpoints.
• Technical Leadership: Lead architecture for large-scale AI systems and align across teams on how models are built and shipped.
• Cloud Architecture: Architect scalable AI infra on AWS (Bedrock, SageMaker, EKS, Kafka, S3) with IaC.
• Evaluation and Quality: Build offline/online evaluation, regression tests, drift detection.
• Cost and Performance: Manage inference cost, latency, and resource sizing (GPU, batching, caching).
• Safety and Governance: Implement logging, access controls, data lineage, and governance gates.
• Best Practices: Promote CI/CD, automated testing, and infrastructure-as-code across AI projects.
• Mentorship & Incident Management: Mentor teams and lead post-incident review and prevention.

Skills

Senior/Staff engineering leadership

AWS production systems

TypeScript/Node.js

LLM systems in production

Model deployment & inference

IaC: Pulumi/Terraform

Vector databases

Monitoring & observability

Kafka/MSK

Mentoring engineers

Education

Bachelor's degree in Computer Science or related field

Tools

AWS

SageMaker

Bedrock

EKS/Kubernetes

S3

Pulumi

Terraform

Kafka/MSK

Job description

DAT Freight & Analytics is seeking a Staff AI Platform Engineer to own the platform for all AI/ML workloads. You will set architectural direction for model gateway, inference, feature storage, and observability across the organization.

You will lead AI system architecture, drive alignment with Product and Engineering, and build scalable, production-grade infrastructure on AWS. This role emphasizes mentorship and incident management while delivering high-impact ML platforms.