Automation AI Engineer

Casado; Brazil; On-site; BRL 180,000 - 320,000; Full time

Benefits offered by this job

Competitive salary

High-impact role

Ownership

Scale AI systems

Job summary

Casado is hiring an AI Full Stack Engineer to build, optimize, and scale AI-powered infrastructure across the full stack. You’ll work on AI communication pipelines, RAG systems, and trend intelligence to empower our Amazon brand management platform.

You’ll own end-to-end pipelines, improve retrieval quality, add observability, and build dashboards for AI metrics. Strong TypeScript/Node.js, React, PostgreSQL, and Linux experience are required.

Qualifications

• Production LLM experience in real systems (Claude/OpenAI)
• RAG system experience (embeddings, retrieval, chunking, context handling)
• 3+ years of software engineering experience
• Proficiency in TypeScript / Node.js
• Strong React skills
• PostgreSQL queries, migrations, indexing
• Experience with API integrations (REST, OAuth, webhooks)
• Linux server experience (SSH, logs, deployments)

Responsibilities

• Build AI pipelines for client performance insights
• Improve RAG retrieval quality
• Add tool use for real-time data in LLM pipelines
• Debug classification errors in AI systems
• Optimize LLM costs and performance
• Build dashboards for AI metrics and usage
• Add observability to pipelines
• Expand content quality systems

Skills

Production LLM experience

RAG system experience

3+ years

TypeScript

Node.js

React

PostgreSQL

API integrations

Linux server experience

Tools

TypeScript

Node.js

React

PostgreSQL

REST APIs

OAuth

Webhooks

Linux

Job description

AI Full Stack Engineer

We've built an AI-native internal platform that powers every aspect of our Amazon brand management business. AI isn't a feature — it's the backbone.LLMs classify and respond to inbound communicationsAI generates pre-call intelligence briefs from raw enrichment dataA RAG system feeds context into every generation pipelineAn AI checkpoint system audits all generated content against quality gates The platform is already live and scaling fast:17+ background services130+ frontend pages214 backend services184 database tablesDozens of autonomous AI pipelines

We're hiring an engineer who operates at the intersection of AI and production systems. You'll build, optimize, and scale AI-powered infrastructure across the full stack.

What You'll Build & Scale

• AI Communication Pipelines
  • Classify inbound messages by category, intent, urgency, and tone
  • Generate contextual responses using enrichment data
  • Implement human approval gates
• AI-Powered Sales Intelligence
  • Transform raw enrichment data into structured pre-call briefs
  • Generate: background, pain hypotheses, talking points, rapport hooks
• RAG System
  • Vector database with embeddingsMarkdown-aware chunkingAsync ingestion workersSemantic search API
• Trend Intelligence Engine
  • Process RSS feeds, social media, video platforms, and search trends
  • Generate reports, forecasts, and content drafts
  • Run autonomously on scheduled jobs
• Content Quality Pipeline
  • Multi-agent system (outline audit generate)
  • Binary quality gates (PASS/FAIL with citations)
  • Supports multiple content formats
• Automated Lead Qualification
  • Enrich leads with product data and market insights
  • AI scoring and qualification grading
  • Automated audit reports
• AI Executive Assistant
  • Slack operations
  • Scheduling workflows
  • Email triage and follow-ups

Key Responsibilities

• Build AI pipelines for client performance insights
• Improve RAG retrieval quality
• Add tool use for real-time data in LLM pipelines
• Debug classification errors in AI systems
• Optimize LLM costs and performance
• Build dashboards for AI metrics and usage
• Add observability to pipelines
• Expand content quality systems

Qualifications

• Production LLM experience (Claude/OpenAI in real systems)
• RAG system experience (embeddings, retrieval, chunking, context handling)
• 3+ years
• TypeScript / Node.js
• Strong React skills
• PostgreSQL (queries, migrations, indexing)
• API integrations (REST, OAuth, webhooks)
• Linux server experience (SSH, logs, debugging, deployments)

Strong Pluses

• Multi-agent LLM systems
• Anthropic Claude expertise
• Vector search / embeddings
• Slack API experience
• Ad platform APIs (Meta, Google, LinkedIn)
• LLM observability (cost, tracing, monitoring)
• Amazon / eCommerce experience
• AI-assisted dev tools (Cursor, Claude Code, etc.)

Benefits

• Competitive salary based on experience
• High-impact role with strong ownership
• Opportunity to scale cutting-edge AI systems to world-class level
• Build AI pipelines for client performance insights
• Improve RAG retrieval quality
• Add tool use for real-time data in LLM pipelines
• Debug classification errors in AI systems
• Optimize LLM costs and performance
• Build dashboards for AI metrics and usage
• Add observability to pipelines
• Expand content quality systems