AI Architect

This is a fully remote position, open to applicants in United States.

📋 Description

• Oversee the maintenance and operation of all current AI pipelines within the platform.

• Transition remaining workflows from the outdated orchestration framework to the primary platform.

• Take ownership of on-call responses for AI pipeline failures, which includes triaging and retrying failed jobs.

• Manage relationships with LLM providers, including API key rotation, cost monitoring, and model upgrades.

• Design and create new high-fan-out AI pipelines to support future horizontal workflows.

• Set standards for onboarding new pipelines, covering registry entries, job subclassing, batch fan-out, and automated reporting.

• Lead architectural decisions regarding data storage, queue partitioning, concurrency control, and cost management.

• Assess and incorporate new LLM providers and embedding models while ensuring backward compatibility with existing vector data.

• Develop observability and operational tools, including custom reporting, cost analysis, and alert systems.

• Collaborate with product, editorial/content, and growth teams to transform requirements into pipeline designs.

• Integrate AI pipelines with the wider technical ecosystem.

• Mentor engineers in AI pipeline design patterns, prompt engineering, and platform architecture.

• Manage the technical proposal process for new pipelines and significant infrastructure modifications.

⛳️ Requirements

• 5+ years of experience in building production applications using a modern web framework such as Rails, Django, or similar.

• Strong expertise in ORM usage, API-only application design, and background job processing.

• Proven track record in designing idempotent, retryable, fan-out job pipelines, which includes batching, concurrency controls, dead-letter handling, and queue partitioning.

• Hands-on experience with various LLM providers, structured outputs, embeddings, prompt engineering, and cost monitoring.

• Familiarity with vector databases for large-scale similarity matching, including batched queries, namespace management, and embedding model migrations.

• Experience managing internal services on a cloud PaaS or similar, with relational databases, caching/queuing infrastructure, and observability tools.

• Demonstrated ability to author technical design documents, make build-vs-buy decisions, and create extensible platforms.

• Must be eligible to live and work in the United States.

• Preferred: 5+ years of experience with Ruby/Ruby on Rails.

• Preferred: Experience transitioning workflows from a Python-based orchestration framework to a Ruby-based framework.

• Preferred: Knowledge of agent orchestration and LLM tracing/observability ecosystems.

• Preferred: Experience with AI alerting or notification systems.

• Preferred: Background in AI applications within the media/publishing industry.

• Preferred: Experience using state machine libraries for managing job lifecycles.

• Preferred: Experience in building retrieval-augmented generation (RAG) pipelines.

🏝️ Benefits

• Company-paid medical, dental, and vision insurance for employees and their dependents.

• Medical benefits include fertility care and $0 copays for in-office mental health consultations with in-network providers.

• Paid parental leave.

• Ample paid time off (PTO) that increases with tenure.

• 401(k) plan with employer matching contributions.

• Flexible Spending Accounts (FSAs) for healthcare and dependent care costs.

• Fitness and wellness stipend.

• Monthly reimbursement for cell phone expenses.

• Company-sponsored lunches in the office every Monday.

• Commuter benefits.

• A supportive, inclusive, and diverse work environment with a strict zero-tolerance policy for harassment.

• Bonus.