Job Overview

Job Type

Full Time

Pay

Not disclosed

Apply Now

Job description

Our purpose is to create technologies that challenge the world's best and change the game for our customers. Therefore, we are looking for professionals who want to be part of a culture guided by excellence and innovation. If you identify with a collaborative work environment driven by curiosity, come build the future of technology with us.

We value the continued growth of zuppers, encouraging each person to follow paths that boost their professional development.

If you have in-depth experience in AI, know how to operationalize models and agents in cloud environments and want to be a protagonist in disseminating knowledge to the entire development community, this opportunity is for you. We are looking for a person passionate about Artificial Intelligence, with a technical profile and advocacy skills, to work at the core responsible for creating, evolving and disseminating AI security guardrails! Work with cutting-edge technologies, help secure intelligent systems, and actively contribute to our company's security culture.

What will you do here

Design, develop and implement AI agents focused on security solutions, using market-leading frameworks and tools;

Integrate and operationalize large language models (LLMs) and knowledge bases, automating and optimizing critical processes through Python and modern APIs;

Evaluate and suggest alternatives on GenAI platforms (such as AWS Bedrock, Azure AI, Google Vertex AI) for customized creation of intelligent agents, considering scalability and security aspects;

Implement and query vectorized databases (e.g. Pinecone, Weaviate, Milvus, ChromaDB) to ensure efficient storage and retrieval of information;

Act as an AI advocate, promoting training, talks and sharing good AI security practices for other development teams;

Automate deployment and monitoring processes for agents and models in cloud environments, using tools such as Docker, Kubernetes, Terraform and CI/CD.

What We Hope You Know

Advanced programming in Python.

Practical experience with LLMs: integration via API, model evaluation and context management.

Implementation of RAG pipelines using vector databases (e.g.: Pinecone, Weaviate, pgvector) and frameworks such as LangChain or LlamaIndex.

Mastery of prompt engineering techniques: few-shot, chain-of-thought, structured output and instruction strategies. Prompt Engineering

Definition and application of sophisticated algorithms aimed at AI contexts.

Versioning practices with Git: branching, code review and conflict resolution.

Implementation and maintenance of CI/CD pipelines for complex back-end applications.

Advanced use of AWS for development, integration and monitoring of solutions.

What would be cool if you knew

Knowledge and experience in Agent Authorization and Authentication;

Previous experience with tools such as Iara or StackSpot;

Active participation in communities, events or technical publications about AI applied to security;

Development of custom integrations, plugins or intelligent observability solutions;

Familiarity with modern caching solutions (e.g. Redis, Memcached) focused on AI;

Cloud, Security or AI certifications.

What we offer you Here it's not just your career that matters, we want you to have physical and mental health and well-being for the best professional and personal experience of your life.