• Build AI applications: chatbots, knowledge assistants, and copilots • Implement multi-LLM orchestration across Azure OpenAI, OpenAI, and other providers • Work with data engineers to leverage datasets for RAG workflows • Integrate AI solutions into business processes using Power Platform • Deploy AI apps on Azure (Functions, App Services, AKS, VMs) • Implement CI/CD and MLOps pipelines using Azure DevOps or GitHub Actions • Monitor performance, reliability, and cost using Azure Monitor and Application Insights • Maintain technical documentation and reusable assets • Stay current with Azure AI, Copilot, and related technologies

• Design multi-agent systems with Subagents/Handoffs/Router patterns • Implement agent logic using langchain/langgraph • Design comprehensive evaluation frameworks • Optimize prompts with A/B testing • Implement state management (short-term and long-term memory) • Design RAG patterns with vector store integration • Guide customers on agent deployment and configuration management • Integrate agents into CI/CD pipelines • Collaborate with Solution Architects on infrastructure requirements • Set up observability using LangSmith • Lead agent engineering maturity assessments • Work directly with enterprise customers to understand requirements and present recommendations • Partner with Solution Architects, Engagement Managers, and Product/Engineering teams

• Fine-tune and train LLMs using our extensive datasets of input and existing output data to continually improve accuracy, speed, and cost-efficiency. • Design and implement improvements to the existing API service, focusing on performance, scalability, and reliability. • Manage the end-to-end lifecycle of the AI models, including data preprocessing, training, evaluation, deployment, and monitoring. • Work with models deployed in various environments, including self-hosted Docker containers and cloud-based services like AWS Bedrock or Azure OpenAI. • Collaborate with software engineers to ensure the AI components are seamlessly integrated into our microservices architecture and meet the required service-level objectives. • Troubleshoot and resolve issues related to model performance, data parsing accuracy, and the API's operational health.

• Diseñar arquitecturas end-to-end para agentes conversacionales y flujos GenAI. • Implementar pipelines de embeddings, retrieval y orquestación con RAG. • Desarrollar soluciones basadas en LLMs (GPT, Claude, Llama, etc.) usando frameworks como LangChain o LlamaIndex. • Integrar soluciones de IA con APIs y microservicios existentes. • Aplicar fine-tuning, prompt engineering y estrategias de optimización de modelos. • Evaluar calidad de respuestas usando frameworks como RAGAS, LangSmith o PromptFlow. • Monitorear y mejorar experiencia de usuario con agentes de IA en producción. • Documentar, versionar y mantener workflows para proyectos de IA de alto impacto.