Data Engineer II

Responsibilities

• Build AI-driven products for the data ecosystem including agents, chatbots, and automated query rewriting systems
• Maintain reliability of agentic systems using guardrails, validations, and observability tools like LangFuse
• Work with MCPs and tool integrations to evolve internal Model Context Protocols
• Participate in technical decisions regarding RAG vs LLM Wiki, cost vs latency, and quality trade-offs
• Conduct code reviews focusing on performance, token cost, and maintainability
• Collaborate with Data Platform and Analytics Engineering teams to connect platform products to real consumption

Requirements

• Proficiency in Python and SQL
• Practical experience building and deploying AI products using LLMs (agents, model APIs)
• Strong programming logic, algorithms, and data structures
• Experience with pipeline orchestration (Airflow, Dagster) and data transformation (dbt or Dataform)
• Familiarity with Cloud architectures (preferably GCP/BigQuery)
• Experience with deployment tools such as Kubernetes, Docker, or Cloud Run
• Understanding of system integration via APIs and webhooks

Preferred Qualifications

• Experience with production agentic systems (prompt engineering, agent orchestration, sub-agents)
• Knowledge of Model Context Protocol (MCP)
• Expertise in RAG architectures and AI system evaluation (LangFuse)
• Spec-oriented development (Spec Kit, SDD)
• Integration with visualization platforms (Metabase, Looker, Tableau) via API
• Infrastructure as Code (Terraform)
• Development of HTTP services (FastAPI) and Slack integrations

About the Company

Arcotech is the technology arm of Arco Educação. We develop digital solutions to help students, parents, and schools work together for more dynamic and effective learning.