AI Engineer – Senior

• Develop AI agents and LLM-based workflows in Python using LangChain and LangGraph
• Map business processes and identify opportunities for AI-powered automation
• Implement RAG pipelines over knowledge bases and internal documents
• Integrate agents with the company’s systems, APIs, and databases
• Evaluate, monitor, and improve response quality, latency, and solution costs
• Deploy solutions to production with testing, version control, and documentation

• Experience developing in Python, including APIs, automation, and integrations
• Hands-on experience with LLMs, including OpenAI, Anthropic Claude, Azure OpenAI, Gemini, or open-source models, as well as prompt engineering
• Experience developing AI agents with LangChain and LangGraph, including tool calling, memory, multi-step workflows, and multi-agent orchestration
• RAG (Retrieval-Augmented Generation), including embeddings, chunking, and vector databases such as pgvector, Pinecone, Chroma, FAISS, or similar technologies
• Experience integrating REST APIs and enterprise systems to automate end-to-end processes
• Experience building services with FastAPI or Flask, Docker, and Git with CI/CD
• Experience with at least one cloud platform, such as AWS, Azure, or GCP, for deploying AI solutions
• Experience with LLM evaluation and observability tools, such as LangSmith, Langfuse, RAGAS, or similar technologies, as well as guardrails
• Experience with MCP (Model Context Protocol) and integrating agents with external tools
• Familiarity with automation and orchestration tools, such as n8n, Airflow, and RPA
• Experience optimizing LLM costs and latency through caching, model selection, and token management
• Understanding of security and data privacy principles applied to AI, including Brazil’s LGPD and sensitive data

• None explicitly stated