AI Engineer

About the Role

We are seeking an AI Engineer to develop solutions based on Generative Artificial Intelligence, integrating Large Language Models, RAG architectures, and multi-agent systems in high-scale corporate environments.

Responsibilities

• • Design, develop, and evolve generative AI solutions in production.
  • Work with LLMs, RAG, AI agents, and multi-agent systems.
  • Build pipelines and applications using Python, LangChain, and LangGraph.
  • Integrate models and frameworks such as Transformers and LlamaIndex.
  • Work on microservices architecture and messaging systems.
  • Collaborate with multidisciplinary teams and provide technical leadership for AI initiatives.

Technical Requirements

• • Solid experience in Software Engineering.
  • Hands-on experience with Generative Artificial Intelligence, including LLMs, RAG, AI agents, and multi-agent systems.
  • Proficiency in Python (mandatory requirement).
  • Experience with LangChain and LangGraph.
  • Solid knowledge of microservices architecture and messaging systems.
  • Familiarity with frameworks and tools for developing with LLMs and SLMs, such as Transformers, LlamaIndex, and related tools.
  • Experience with relational and non-relational databases.
  • Knowledge of Docker and Kubernetes.

Soft Skills

• • Ability to collaborate effectively with multidisciplinary teams.
  • Excellent communication and interpersonal skills.
  • Technical leadership profile, serving as a reference for the team.
  • Strong analytical skills and ability to solve complex problems.
  • Proactivity, autonomy, and results-oriented mindset.

Work Location

This is a hybrid role, with 3 on-site days per week at the Santander Interlagos office in São Paulo. The candidate must reside in São Paulo or the surrounding region.