AI Development Specialist – AI Engineer

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

📋 Description

• Create and implement generative AI solutions utilizing large language models (LLMs), with an emphasis on practical business applications.

• Develop comprehensive RAG pipelines that encompass ingestion, processing, indexing, retrieval, and response generation.

• Design and coordinate intelligent agents, including multi-agent scenarios and task-focused workflows.

• Establish integrations between LLMs and enterprise systems through APIs, databases, and distributed services.

• Organize data pipelines for embeddings, vector searches, and semantic retrieval.

• Assess, test, and enhance model and application performance regarding latency, cost, and response quality.

• Apply prompt engineering techniques and manage prompt versioning.

• Uphold engineering best practices, which include code quality, testing, and documentation.

• Implement governance, security, and usage controls within AI solutions.

• Automate workflows and integrations using tools like n8n or similar when applicable.

⛳️ Requirements

• Practical experience with large language models (LLMs), including OpenAI or comparable open-source models.

• Familiarity with RAG architectures and vector databases (Pinecone, Weaviate, FAISS, or similar).

• Strong expertise in Python and/or Node.js, ideally with a focus on AI applications.

• Experience in integrating REST APIs and working with distributed systems.

• Proficiency with orchestration frameworks such as LangChain, LlamaIndex, or similar.

• Knowledge of constructing data pipelines and processing information for AI applications.

• Background in developing scalable, service-oriented applications.

🏝️ Benefits

• Remote work opportunities.

• Flexible working hours.