Staff AI Platform Engineer: Scale ML Infra & Observability

Socket.dev; Seattle (WA); Hybrid; USD 198,000 - 246,000; Full time

Benefits offered by this job

Medical, Dental, Vision

Parental Leave

Flexible Vacation

401k matching

Transit benefits

Job summary

DAT Freight & Analytics is seeking a Staff AI Platform Engineer to own the platform powering all AI workloads. You will shape architecture from gateway to storage, and lead the design and governance of scalable, observable AI infrastructure on AWS.

You will mentor engineers and data scientists, drive best practices in CI/CD, testing, and incident response, and partner with Product and Engineering across the company to ship reliable AI services.

Qualifications

• 10+ years of software engineering experience with production infrastructure ownership.
• 4+ years building and operating ML/AI platforms in production.
• Proficiency in TypeScript/Node.js, Java, or Go, with library design mindset.
• Strong AWS production experience incl. EKS/Kubernetes, Lambda, S3, Kafka/MSK.
• Experience with containerized inference, GPU scheduling, autoscaling, batching.
• Hands-on with LLM systems in production: retrieval-augmented generation, vector DBs, tool-calling.
• Experience building evaluation/monitoring: offline/online metrics, drift checks.
• Background in event-driven distributed systems using Redpanda or Kafka.

Responsibilities

• Own the platform design and operations for AI workloads across teams.
• Lead architecture discussions and align Product, Eng, and Business stakeholders.
• Architect scalable AI infrastructure on AWS and define IaC with Pulumi.
• Build offline/online evaluation systems and A/B/shadow testing pipelines.
• Own cost and performance metrics, optimize GPU/serverless capacity and latency.
• Implement guardrails, logging, data governance, and security across models.
• Promote modern software practices: CI/CD, automated testing, code reviews.
• Mentor engineers in production ML and distributed systems.
• Lead incident response and root-cause analysis for AI services.

Skills

Platform ownership

AWS expertise

LLM systems

Observability

Mentoring

Communication

Education

Bachelor's degree in CS/Engineering

Tools

Pulumi

Terraform

Kubernetes

S3

Redpanda

Kafka

Job description

DAT Freight & Analytics is seeking a Staff AI Platform Engineer to own the platform powering all AI workloads. You will shape architecture from gateway to storage, and lead the design and governance of scalable, observable AI infrastructure on AWS.

You will mentor engineers and data scientists, drive best practices in CI/CD, testing, and incident response, and partner with Product and Engineering across the company to ship reliable AI services.