Principal Data & AI Architect

Posted 9hrs ago

Employment Information

Education
Salary
Experience
Job Type

Report this job

Job expired or something wrong with this job?

Job Description

Principal Data & AI Architect designing secure agent runtimes, APIs, and scalable pipelines for Publicis Groupe’s marketing technology products. Mentoring engineers and setting cross-platform architecture.

Responsibilities:

  • Set the technical direction for OneSuite data products and their integration into the Performics platform
  • Write code and design cross-repository architecture for reliable, scalable systems
  • Lead high-stakes technical decisions and establish engineering standards
  • Build backend and data foundations for AI-assisted analyst workflows using agent and tool runtimes
  • Own architecture across marketing data pipelines, connector systems, platform APIs, and agent/tool runtimes
  • Define domain boundaries and data contracts between warehouse outputs, APIs, agent tools, and user-facing workflows
  • Create incremental technical plans balancing reliability, security, tenant isolation, developer experience, and maintainability
  • Evolve medallion-architecture data pipelines, including data quality, schema enforcement, lineage, and curated outputs
  • Harden ingestion from external marketing platforms and APIs
  • Architect backend services, cloud infrastructure, stable contracts, streaming workflows, and tool permissions
  • Design agent and tool-runtime systems with secure multi-tenant access and durable boundaries
  • Implement authentication, authorization, rate limiting, and multi-tenant access controls
  • Integrate external APIs, cloud services, internal microservices, and agent/tool runtimes
  • Build and maintain deployment pipelines and infrastructure environments
  • Implement tracing, structured logging, metrics, and alerting
  • Mentor engineers, contribute to internal libraries and backend frameworks, and drive platform consistency

Requirements:

  • At least ten years of experience in backend, data platform, or distributed systems
  • At least two years of hands-on production experience building with LLMs and agent frameworks
  • Experience integrating Claude Agent SDK, MCP-style tooling, or similar agent/tool runtimes into live systems
  • Experience architecting agent and tool-runtime systems with tool permissioning and secure multi-tenant access
  • Expertise in Python, API design, service boundaries, async and concurrent systems, and modern testing
  • Proficiency with Databricks, PySpark, Lakehouse patterns, and medallion-style data architecture, or equivalent large-scale data pipeline experience
  • Strong AWS serverless experience with Lambda, API Gateway, S3, IAM, and CloudFormation/SAM or equivalent infrastructure-as-code tooling
  • Deep understanding of multi-tenant SaaS design, authentication and authorization, tenant-scoped data access, secrets management, and operational security
  • Experience designing stable data contracts, schema evolution patterns, and consumer-facing data models
  • Proficiency with SQL and NoSQL databases such as PostgreSQL, Redis, or MongoDB
  • Strong CI/CD experience and knowledge of observability practices including logs, metrics, and traces
  • Technical leadership through mentoring, architecture decisions, code reviews, communication, and engineering standards
  • Fluent in English, both verbal and written
  • Familiarity with Fivetran, custom connector development, or third-party data ingestion operations is advantageous
  • Knowledge of Delta Lake, Unity Catalog, data governance, data lineage, Lakehouse performance optimization, streaming or queuing systems, and marketing or advertising APIs would be beneficial

Benefits:

  • Diversity and inclusion commitment
  • Continuous learning and knowledge sharing
  • Mentoring and professional growth opportunities
  • Remote work arrangement