AI Architect

Jobtailor; Deutschland; Remote; EUR 90.000 - 130.000; Vollzeit

Zusammenfassung

Jobtailor is seeking a senior AI pipelines engineer to maintain and evolve production-grade AI workloads. You will own end-to-end pipeline design, include on-call responses for failures, and manage vendor relationships for LLM providers and cost controls.

The role emphasizes building scalable, fan-out pipelines and advancing the platform architecture. You will collaborate with product and growth teams to translate requirements into robust designs, drive onboarding conventions, and mentor

Qualifikationen

• 5+ years building production applications in a modern web framework such as Rails, Django, or similar
• Strong experience with ORM usage, API-only application design, and background job processing
• Proven experience designing idempotent, retryable, fan-out job pipelines, including batching, concurrency controls, dead-letter handling, and queue partitioning
• Hands-on experience with multiple LLM providers, structured output, embeddings, prompt engineering, and cost tracking
• Experience with a vector database for similarity matching at scale, including batched queries, namespace management, and embedding model migration
• Experience running internal services on a cloud PaaS or equivalent, with relational databases, caching/queueing infrastructure, and observability tooling
• Track record of authoring technical design documents, making build-vs-buy decisions, and designing extensible platforms
• Must be eligible to live and work in the United States
• Preferred: 5+ years of Ruby/Ruby on Rails experience
• Preferred: Experience migrating workflows from a Python-based orchestration framework to a Ruby-based framework
• Preferred: Familiarity with agent orchestration and LLM tracing/observability ecosystems
• Preferred: Experience with AI alerting or notification systems
• Preferred: Background in media/publishing AI applications
• Preferred: Experience with state machine libraries for managing job lifecycles
• Preferred: Experience building retrieval-augmented generation (RAG) pipelines

Aufgaben

• Maintain and operate all existing AI pipelines on the platform
• Migrate remaining workflows from the legacy orchestration framework to the primary platform
• Own on-call response for AI pipeline failures, including failed-job triage and retries
• Manage LLM provider relationships, API key rotation, cost tracking, and model upgrades
• Design and implement new high-fan-out AI pipelines for future horizontal workflows
• Establish conventions for onboarding new pipelines, including registry entries, job subclassing, batch fan-out, and automated reporting
• Drive architectural decisions around data storage, queue partitioning, concurrency throttling, and cost controls
• Evaluate and integrate new LLM providers and embedding models while maintaining backward compatibility with existing vector data
• Build observability and operational tooling, including custom reporting, cost tracking, and alerting
• Partner with product, editorial/content, and growth teams to translate requirements into pipeline designs
• Integrate AI pipelines with the broader technical stack
• Mentor engineers on AI pipeline patterns, prompt engineering, and platform architecture
• Own the technical proposal process for new pipelines and major infrastructure changes

Kenntnisse

AI Pipeline Management

LLM Provider Integration

Job Pipeline Design

Cloud PaaS Experience

Technical Documentation

Prompt Engineering

Cost Tracking

Tools

Ruby on Rails

Django

Cloud PaaS

Observability Tools

State Machine Libraries

Vector Database

Jobbeschreibung

• Maintain and operate all existing AI pipelines on the platform


• Migrate remaining workflows from the legacy orchestration framework to the primary platform


• Own on-call response for AI pipeline failures, including failed-job triage and retries


• Manage LLM provider relationships, API key rotation, cost tracking, and model upgrades


• Design and implement new high-fan-out AI pipelines for future horizontal workflows


• Establish conventions for onboarding new pipelines, including registry entries, job subclassing, batch fan-out, and automated reporting


• Drive architectural decisions around data storage, queue partitioning, concurrency throttling, and cost controls


• Evaluate and integrate new LLM providers and embedding models while maintaining backward compatibility with existing vector data


• Build observability and operational tooling, including custom reporting, cost tracking, and alerting


• Partner with product, editorial/content, and growth teams to translate requirements into pipeline designs


• Integrate AI pipelines with the broader technical stack


• Mentor engineers on AI pipeline patterns, prompt engineering, and platform architecture


• Own the technical proposal process for new pipelines and major infrastructure changes

Requirements

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


• Strong experience with ORM usage, API-only application design, and background job processing


• Proven experience designing idempotent, retryable, fan-out job pipelines, including batching, concurrency controls, dead-letter handling, and queue partitioning


• Hands-on experience with multiple LLM providers, structured output, embeddings, prompt engineering, and cost tracking


• Experience with a vector database for similarity matching at scale, including batched queries, namespace management, and embedding model migration


• Experience running internal services on a cloud PaaS or equivalent, with relational databases, caching/queueing infrastructure, and observability tooling


• Track record of authoring technical design documents, making build-vs-buy decisions, and designing extensible platforms


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


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


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


• Preferred: Familiarity with agent orchestration and LLM tracing/observability ecosystems


• Preferred: Experience with AI alerting or notification systems


• Preferred: Background in media/publishing AI applications


• Preferred: Experience with state machine libraries for managing job lifecycles


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

Core Competencies

Demonstrates expertise in building and maintaining AI pipelines, including designing idempotent job pipelines and managing LLM provider relationships. Proficient in cloud PaaS environments and capable of driving architectural decisions for data storage and observability tooling.

Highest-signal resume keywords

• AI Pipeline Management


• LLM Provider Integration


• Job Pipeline Design


• Cloud PaaS Experience


• Technical Documentation Authoring

Hard Skills

• Production Application Development


• ORM Usage


• API-Only Application Design


• Background Job Processing


• Idempotent Job Pipeline Design


• Vector Database Experience


• Embedding Model Migration


• Cost Tracking


• Concurrency Controls


• Batch Processing

Soft Skills

• Mentoring Engineers


• Cross-Functional Collaboration

Industry Keywords

• AI Applications


• Media/Publishing AI


• Agent Orchestration


• RAG Pipelines

Tools & Technologies

• Ruby on Rails


• Django


• Cloud PaaS


• Observability Tooling


• State Machine Libraries