Founding Data & AI Engineer – Creative Engine

Posted 1hrs ago

Employment Information

Education
Salary
Experience
Job Type

Report this job

Job expired or something wrong with this job?

Job Description

Founding engineer building a data and AI creative intelligence engine for a performance creative agency. Developing pipelines, video analysis, semantic search, and full-stack dashboards.

Responsibilities:

  • Design data pipelines that pull, store, and structure performance, sales, and engagement data across hundreds of client accounts and platforms.
  • Build the LLM analysis layer using Gemini for video analysis and Claude for generation, with structured output and cost controls.
  • Build semantic search and discovery with pgvector.
  • Connect organic references, top-performing ads, content tags, and creator history into queryable creative intelligence.
  • Develop creator-performance matching for casting decisions.
  • Own full-stack features including dashboards, tag browsers, enrichment queues, and export tools using Django, HTMX, and Tailwind.
  • Integrate external APIs including TikTok, Meta, Motion, and Cruva.
  • Maintain internal asynchronous pipelines using Celery and Redis.
  • Ship features end to end in a small, autonomous, low-process team.

Requirements:

  • 5+ years building production, data-heavy applications with Python/Django and PostgreSQL
  • Strong SQL skills including aggregations, joins, and window functions
  • Ability to design schemas and data models from use cases
  • Experience designing and debugging asynchronous data pipelines with Celery + Redis or equivalent
  • Hands-on production experience with LLM APIs, prompt engineering, structured output, and cost management
  • Fluency with agentic coding tools such as Claude Code and Cowork
  • Experience integrating third-party APIs with rate limits, authentication flows, and inconsistent data
  • Comfortable owning frontend work with Django templates, HTMX, and Tailwind
  • Strong written communication and high ownership on a small async team
  • Advanced to fluent English skills
  • Based in Brazil and working US time zones
  • Preferred: agent harnesses, RAG, or LLM evaluation pipelines
  • Preferred: familiarity with ML fundamentals
  • Preferred: video or audio processing pipeline experience
  • Preferred: ad tech, creator economy, performance marketing, or marketplace experience
  • Preferred: experience working with a US-based team
  • Updated CV in English required for application

Benefits:

  • Remote work
  • Async work environment
  • Continuous learning opportunities and resources to thrive
  • AI-assisted workflow using Claude Code and coding agents
  • Production deployments multiple times per day
  • Optional introductory video submission; phone quality acceptable