Job Description

Job Description
We are looking for a person with experience in developing artificial intelligence solutions, both in Machine Learning and generative models, participating in the design, development and integration of applications based on language models and semantic search systems.
Responsibilities:
Develop and maintain artificial intelligence solutions based on Machine Learning and generative models.
Build and improve LLM-based applications, including prompt engineering, flow orchestration, and use of external tools.
Implement and optimize RAG pipelines, including document fragmentation, embeddings, ranking and recovery strategies.
Work with vector databases for semantic search and generation of contextual responses.
Develop integrations through MCP or similar systems to connect AI models with APIs and external platforms.
Train, evaluate and deploy Machine Learning models for prediction, classification, clustering and other use cases.
Integrate AI capabilities into existing applications through API development.
Support the deployment, monitoring and optimization of AI services in cloud or local environments.
Implement basic validation, control and monitoring mechanisms to improve the quality and reliability of AI systems.
Deploy and operate AI workloads in Azure, AWS, or GCP.
Requirements:
Between 2 and 4 years of development experience with Python and libraries such as Pandas, NumPy and Scikit-learn.
Experience in developing and deploying Machine Learning models in real cases.
Experience in LLM-based applications, including prompt engineering and model integration.
Experience with frameworks such as LangChain or similar.
Experience in designing or implementing RAG pipelines, including chunking, embeddings and information retrieval.
Experience with vector databases such as pgvector, FAISS, Pinecone or Weaviate.
Knowledge of embeddings, semantic search and information retrieval.
Experience with MCP or similar AI systems integration tools.
Experience in development and consumption of APIs.
Experience deploying and operating AI or ML services in Azure, AWS, or GCP.
Knowledge of deployment models in cloud or local environments.
Knowledge of monitoring, logging and observability.
Good communication and teamwork skills.

Salary to receive
To agree