Job Summary: We are seeking a hybrid profile to lead the implementation of LLMs, RAG, MCP, and Machine Learning, while maintaining, supporting, and developing AI-based functionalities. Key Highlights: 1. Lead the implementation of LLMs, RAG, MCP, and Machine Learning. 2. Build Generative AI tools to optimize models. 3. Integrate AI with traditional development and architect RAG workflows. We seek a hybrid profile with solid foundations in .NET and Angular, combined with the vision and technical capability to lead the implementation of LLMs, RAG, MCP, and Machine Learning within our ecosystem. The Challenge: Your mission will be the maintenance, support, and evolutionary development of AI-based functionalities. You will not only consume APIs; you will build Generative AI tools that feed our current infrastructure, optimizing model responses to large volumes of PL/SQL data through RAG and MCP architectures. Technical Requirements: AI Specialization: - LLMs (Large Language Models) & GenAI: Implementation of Large Language Models. - RAG (Retrieval-Augmented Generation) Architectures: Experience connecting models with external data. - MCP (Model Context Protocol): Ability to standardize the connection between models and data sources. - Machine Learning: Solid knowledge of Scikit-learn and Deep Learning frameworks (PyTorch or TensorFlow). Core Development: - Frontend: Experience with Angular for building intuitive UI/UX interfaces consuming AI services. - Backend: Proficiency in .NET (C#) for business logic and PL/SQL for relational database management, plus knowledge of non-relational databases. - AI Language: Python (essential for model orchestration). Desirable (Plus factors that will set you apart): - Experience with Google Cloud Platform (Vertex AI, consumption of AI APIs). - Creation of microservices using FastAPI. - Handling of embeddings and vector databases. - Model optimization with ONNX. - English: Technical proficiency. Your Responsibilities: 1. Integrate: Bridge the world of AI with traditional development, ensuring that .NET logic and Angular UI seamlessly interact with AI models. 2. Architect: Implement Retrieval-Augmented Generation (RAG) workflows so that our LLMs respond based on real business data. 3. Manage: Administer AI resources on Google Cloud, maintaining strict control over costs, availability, and API quotas. 4. Evolve: Maintain and enhance existing ML tools, migrating or converting models to efficient formats such as ONNX when necessary. Building an MCP. -Requirements- Minimum Education: University / Technical Degree 1 year of experience Skills: .net Keywords: specialist, developer, programmer, senior, sr