This is a fully remote position, open to applicants in Brazil.

📋 Description

• Create applied AI solutions, encompassing agents and systems based on large language models (LLMs).

• Coordinate intelligent workflows.

• Design backend systems and AI pipelines for data ingestion, vectorization, querying, and response generation.

• Integrate various systems using REST APIs and webhooks, while connecting structured databases.

• Deploy, monitor, ensure observability, and scale production solutions on the Microsoft Azure platform.

• Develop and manage solutions utilizing Azure OpenAI, Azure Functions, App Services, AI Search, Storage/Data Lake, Docker, and GitHub Actions.

• Engage in end-to-end software architecture and implementation.

⛳️ Requirements

• Proven experience in developing applied AI solutions (agents and LLM-based systems) and orchestrating intelligent workflows.

• Expertise in Python or Node.js for backend development and constructing AI pipelines (data ingestion, vectorization, querying, and response generation).

• Familiarity with agent and orchestration frameworks such as LangChain/LangGraph, CrewAI, and n8n.

• Knowledge of RAG architectures (chunking, embeddings, re-ranking, and optimizing context windows) and vector databases like Pinecone, Weaviate, Chroma, or Azure AI Search.

• Understanding of AI providers and models, including OpenAI/Azure OpenAI, open-source models (LLaMA, Mistral via Ollama), advanced prompt engineering, and tool/function calling.

• Practical experience in integrating systems via REST APIs, webhooks, and structured databases (e.g., SQL).

• Background in deploying, monitoring, ensuring observability, and scaling production solutions within the Microsoft Azure cloud environment (Azure OpenAI, Functions, App Services, AI Search, Storage/Data Lake).

• Experience with containers (Docker) and CI/CD pipelines (GitHub Actions).

• Strong understanding of software architecture with the capability to work across the entire development cycle.