# Gilberto Carrillo > AI Engineer & Team Lead with 3 years building production LLM platforms, workflow engines and agents in Python, FastAPI and Azure. Based in Venezuela, open to remote AI engineering roles building agentic products and LLM platforms. I build the backend behind agentic products: the infrastructure that turns "wire an LLM into a feature" into something reliable enough for real clients. ## Contact - Website: https://gilbertocarrillo.com/ - Email: gilbertojosecarrilloparra@gmail.com - LinkedIn: https://www.linkedin.com/in/gilberto-carrillo - GitHub: https://github.com/gilbertocarrillo - CV (PDF): https://gilbertocarrillo.com/assets/Gilberto_Carrillo_CV.pdf ## Profile - Role: AI Engineer & Team Lead - Focus: Agentic AI, LLM platforms, Python backend - Based in: Venezuela, working remotely - Languages: Spanish (native), English (professional working proficiency) - Education: B.Sc. Systems Engineering, Universidad de los Andes - Certifications: Neural Networks and Deep Learning (DeepLearning.AI); Machine Learning Specialization (DeepLearning.AI & Stanford Online) ## Experience ### MAIDEPOT — Remote, South Korea-based platform for AI workflows and agents (Jul 2023 – Aug 2026) **Backend Engineer & Team Lead — AI Platform (Jan 2024 – Aug 2026)** - Promoted to Team Lead within six months; led a cross-functional engineering team (frontend, full-stack and QA) while remaining the main backend contributor and owning architecture decisions. - Built a model-agnostic LLM layer across 7 providers (OpenAI, Azure OpenAI, Anthropic, Gemini, DeepSeek, GLM, LG EXAONE), with retries, rate-limit failover and load balancing, and the multi-model chat on top of it. - Re-architected the workflow engine into a JSON-defined DAG with parallel execution, LLM-evaluated branches and map-reduce loops; KOTRA and The Korea Times built their own workflows on it. - Delivered translation of documents up to 1,000 pages and transcription of long audio and video, two of the platform's most-used features. - Extended the platform to PydanticAI agents with ~40 native tools, workflows as tools and scheduled routines; delivered client agents such as a sales-training assistant for LG and Spanish tutors for Korean language academies. - Built RAG knowledge bases (pgvector, Cohere rerank) and a vector-free LLM wiki engine. - Owned the core FastAPI backend: SSE streaming, business-level multi-tenancy, Redis locks and rate limiting. - Built the public API (hashed API tokens, rate limits per operation), usage-based billing priced per model and token type, the document drive and the enterprise dashboard. - Managed releases on Azure App Service across dev, staging and production with zero-downtime slot swaps; ran heavy workloads on Azure Functions with Storage Queues. **Backend Engineer (Jul 2023 – Dec 2023)** - Migrated the platform's core backend, including its original text and image generation apps, from Google Cloud Functions to a dedicated FastAPI service, eliminating cold starts and consolidating the logic into a single, maintainable API. ## Research - **Reinforcement Learning for Estimating Student Proficiency in Math Word Problems** — Perez, J., Dapena, E., Aguilar, J., & Carrillo, G. 2022 XVII Latin American Conference on Learning Technologies (LACLO), IEEE Xplore. https://doi.org/10.1109/LACLO56648.2022.10013399 - **Design of Human-Robot Interaction for Learning Multiplication Tables and Implementation of Speech Recognition Models** — B.Sc. thesis, Universidad de los Andes, 2022. 2nd place, VII National Contest of Special Degree Projects, Venezuelan Computing Society. https://doi.org/10.13140/RG.2.2.27502.95042 ## Skills - Agents: PydanticAI, MCP, workflow orchestration, tool use / function calling - Models & retrieval: multi-provider LLM orchestration, RAG, pgvector, embeddings & reranking, prompt engineering, context management, Azure Document Intelligence, AssemblyAI - Backend: Python, FastAPI, PostgreSQL, Redis, Elasticsearch - Cloud & infra: Azure (App Service, Functions, OpenAI), Firebase, Docker, Git/GitHub - Interface: Next.js, React, JavaScript, Redux, Vercel - How I work: system design, software architecture, technical leadership, cross-functional collaboration - AI-assisted development: Claude Code, Codex, OpenCode