AI Engineer

• At least 3 years of experience in Generative Artificial Intelligence projects.
• Solid knowledge of software engineering, Clean Code principles, and architecture design.
• Demonstrable experience designing architectures for GenAI solutions, selecting agents, foundation models, vector databases, and orchestration tools.
• Proficiency in Python and experience with TypeScript.
• Experience working with vector databases and optimizing semantic, hybrid, and similarity searches.
• Advanced knowledge of frameworks such as LangChain, LangGraph, or LangFlow.
• Experience in the construction and orchestration of autonomous agents and multi-agent systems.
• Hands-on experience in corporate integration through APIs, Tool Calling, and MCP servers.
• Knowledge of advanced RAG techniques, automated document ingestion, and knowledge graph-based architectures, such as GraphRAG.
• Experience in preprocessing complex unstructured data.
• Knowledge of security, validation, and hallucination prevention mechanisms.
• Experience applying LLMOps practices: observability, evaluation, traceability, and monitoring of LLM-based solutions.
• Knowledge of tools such as Langfuse, LangSmith, or similar.
• Experience working with Git, Docker, and CI/CD pipelines.
• Experience creating unit tests, integration tests, and continuous deployment processes.

You will be part of innovative projects where you will work on the entire lifecycle of Generative AI solutions: from design and experimentation to production through LLMOps practices.

At Paradigma, we are looking to hire an AI Engineer specialized in Generative Artificial Intelligence, with experience in building and deploying solutions based on LLMs, RAG architectures, and agentic systems.

As an AI Engineer, you will act as a technical reference in the creation of Generative AI solutions and will participate in functions such as:

• Designing and developing solutions based on LLMs and foundation models.
• Implementing advanced RAG pipelines, GraphRAG architectures, and hybrid retrieval systems.
• Building autonomous agents and solutions based on multi-agent architectures.
• Orchestrating complex flows using frameworks such as LangChain and LangGraph.
• Managing context, state, and agent memory to ensure coherent interactions.
• Integrating AI solutions with APIs, services, and corporate data sources through Tool Calling.
• Designing, deploying, and maintaining servers based on Model Context Protocol — MCP.
• Processing, transforming, and ingesting unstructured data from various documentary sources.
• Implementing validations, controls, and guardrails to reduce hallucinations and protect sensitive data.
• Designing evaluation, observability, and traceability mechanisms for LLM models and applications.
• Packaging, deploying, and putting Generative AI solutions into production by applying LLMOps best practices.
• Developing unit and integration tests and participating in continuous integration and deployment processes.

We trust people to organize their work flexibly, favoring the balance between personal and professional life without losing sight of the objectives and the impact of our work. You will have the possibility to work in a remote or hybrid work model.