Engenheiro de IA - 100% Remoto

Artificial Intelligence (AI) Engineer - 100% Remote We are seeking highly senior profiles who will take ownership and lead our AI frontier, combining different data architectures, language models, and tool integration to create intelligent agents. Here, you'll have the freedom and autonomy to explore cutting-edge technologies, but also the responsibility to be the driving force that turns solutions from concept to real value generation. This position is 100% remote! We are investing increasingly in Artificial Intelligence. And to accelerate our growth even further, we're looking for people who want to build a fulfilling career in Tech. What we expect from a Senior/Specialist profile here: • Ownership: You don't wait for a refined task card. You investigate the business problem, run POCs, propose the agent architecture, choose the model, execute, test, and validate, ensuring alignment with stakeholders. • Resilience and Autonomy: Complex integrations or access constraints aren't blockers—they're steps to solve. We expect you to coordinate with Cloud, Security, and Data Engineering teams to remove barriers and enable your experiments in production. • End-to-End Vision: You understand everything from raw data capture (via Scraping, APIs, or Snowflake) to token cost impact and final user experience (e.g., WhatsApp or internal systems). • Technical Leadership: As a reference, you raise the team's standards, introducing engineering best practices, suggesting new tools, and mentoring junior profiles. As an AI Engineer, you will focus on: • Developing intelligent autonomous agents using modern frameworks like LangChain and Agno, creating workflows that combine multiple tools. • Creating conversational agents with short-term and long-term memory, ensuring traceability and personalization for customers. • Experimenting with and integrating different LLMs (OpenAI, Gemini, DeepSeek, etc.), technically evaluating use cases and performance/cost trade-offs. • Structuring and optimizing vector databases (ChromaDB, FAISS) and implementing advanced RAG techniques, connecting agents to corporate data in Snowflake or internal systems. • Intelligent extraction mechanisms: Using web scraping (Crawl4AI) and complex document parsing (Docling) to feed knowledge pipelines. • Action Automation: Integrating agents with APIs so they not only respond but autonomously execute tasks and update systems. • Engineering Culture: Building experimentation, versioning, and publishing pipelines (MLOps) with a focus on scalability and clean code. • Working with business teams to understand needs and transform them into practical AI agent solutions. Requirements: • Bachelor's degree in Engineering, Statistics, Mathematics, or Technology-related field. • Proficiency in Python and familiarity with AI and data-focused libraries such as Transformers, Agno/LangChain/LlamaIndex, and scikit-learn. • Experience with frameworks for autonomous agents and tool architectures. • Experience with NLP and hands-on experience integrating market LLMs (OpenAI, Gemini, DeepSeek, Cohere) in production applications. • Experience with API integrations (requests and FastAPI), data manipulation, and database connections (Snowflake preferred). • Experience with vector databases for semantic search and RAG. • Software engineering best practices, collaborative versioning with GitHub, and scalable solution architecture. • Knowledge of LLM deployment in production and prompt engineering techniques. Differentials: • Machine Learning experience (supervised learning, unsupervised learning, and reinforcement learning). • MLOps experience for automating model lifecycle. • Knowledge of LLM optimization (quantization, fine-tuning, etc.). • Experience with conversational AI projects integrated with WhatsApp. • Previous experience as a technical reference in multidisciplinary teams.