Jaime S.

• • Coordinated a production multi-agent AI system that translates natural language into SQL over advertising data warehouses, coordinating a pipeline of specialized LLM agents — each responsible for a distinct step: intent under standing, context retrieval, semantic layer generation, example selection, and SQL generation

• • Implement a semantic layer consistency engine that automatically detects and resolves duplicate or conflicting schema definitions produced by LLM agents across multiple data sources, ensuring generated SQL always refer ences a single, coherent view of the data

• • Built a SQL validation pipeline: executes queries against the live warehouse, uses an LLM judge to verify results match user intent, runs business-logic rules, and applies chart-ready data transformations in a single automated flow

• • Designed configurable failure handling across the full query pipeline, allowing individual steps to fail gracefully with per-step policies that determine whether to surface a partial result or retry

• • Architected a serverless LLM dispatch system on AWS Lambda with a provider abstraction layer that decouples agent logic from any specific model — enabling seamless swapping between OpenAI, Gemini, and Anthropic with out touching agent code

• • Built an ActionsAgent: a parallel LLM pipeline that evaluates ad entity signals like spend, revenue, roas, etc against configurable scenarios and generates fully-structured campaign recommendations — typed action parameters, signal-grounded rationales, impact estimates, and step-by-step execution plans — with a self-correcting genera tion loop that re-prompts on schema errors, followed by an LLM judge verifying action selection, signal grounding, and parameter rationale quality

• • Technologies: Python (asyncio, Pydantic, FastAPI), OpenAI/LiteLLM, AWS (ECS, Lambda, CDK), Docker, PostgreSQL

• • Built a Redis-backed internal memory system persisting tool calls, results, and arguments across workflow execu tions

• • Engineered stateful dynamic agentic flows with global request state, enabling LLMs to adapt tool usage without predefined paths

• • Improved initial streamed message latency from 5s to 2s via background task orchestration for parallel workflows

- Sistemas integrados de memoria a corto y largo plazo, aprovechando Redis y retrieval basado en embeddings.

- Diseñé e implementé NPCs Agénticos con autonomía tanto dentro del juego (toman decisiones activas para interactuar con el entorno en función de la visión, la memoria, las interacciones del usuario, etc.) como con integración al mundo real (por ejemplo, Twitter, YouTube, Spotify) mediante MCPs y flujos de trabajo agénticos.

- Desarrollé una capa de control de servicios en Python para manejar el enrutamiento inteligente, recuperación ante errores y coordinación de servicios entre módulos de IA (por ejemplo, voz, memoria, orquestación).

Tecnologías: Python, Redis, Langfuse, ElevenLabs, FastAPI, Docker