AI Platform Architect - Scale End-to-End Pipelines

The Information; Freehold (NJ); On-site; USD 155,000 - 175,000; Full time

Benefits offered by this job

Medical coverage

Dental and vision

Parental leave

Generous PTO

401(k) matching

FSAs

Wellness stipend

Cell phone reimbursement

Office lunches

Diversity & inclusion

Job summary

The Information is seeking an AI Architect to lead the design, evolution, and scaling of its AI pipeline infrastructure. You will own a backend platform that orchestrates AI workflows at scale and extend it to support high-fan-out AI features central to our product strategy.

You’ll manage migrations, on-call responses, and cost tracking, while collaborating with product, editorial, and growth teams to deliver reliable AI capabilities across the platform.

Qualifications

• 5+ years building production applications in a modern web framework (e.g., Rails, Django) with ORM and API-only design.
• Proven experience designing idempotent, retryable, fan-out job pipelines.
• Hands-on work with multiple LLM providers, structured output, embeddings, and cost tracking.
• Experience with vector databases for similarity matching at scale.
• Production operations mindset with cloud PaaS, relational DBs, and observability tooling.
• Track record of authoring technical design docs and build-vs-buy decisions.

Responsibilities

• Maintain and operate all existing AI pipelines on the platform.
• Migrate remaining workflows from legacy orchestration to the primary platform.
• Own on-call response for AI pipeline failures and retries.
• Manage LLM provider relationships, API key rotation, cost tracking, and model upgrades.

Skills

Backend framework expertise

Job orchestration at scale

LLM integration experience

Vector search infrastructure

Production operations mindset

Architecture & design docs

Tools

Ruby on Rails

Python

Job description

The Information is seeking an AI Architect to lead the design, evolution, and scaling of its AI pipeline infrastructure. You will own a backend platform that orchestrates AI workflows at scale and extend it to support high-fan-out AI features central to our product strategy.

You’ll manage migrations, on-call responses, and cost tracking, while collaborating with product, editorial, and growth teams to deliver reliable AI capabilities across the platform.