platform
AI Platforms
Internal developer platforms for building, deploying, and monitoring ML models and LLM-based services at scale.
About
Building AI that ships to production.
Hi, I'm Javier. I work on applied AI systems — turning machine learning and LLM technologies into reliable production software.
My work sits at the intersection of machine learning engineering, backend systems, and AI platform design. I focus on designing systems that are technically sound, scalable, and maintainable in real production environments.
Focus areas
- LLM systems & applications
- Retrieval-Augmented Generation (RAG)
- Applied AI platforms
- Machine learning engineering
- Backend systems for AI
Selected work
Types of systems I build.
data
Document Pipelines
High-throughput document ingestion, extraction and indexing systems for RAG, search, and knowledge management.
llm
LLM Applications
Production-grade applications powered by large language models — from agentic workflows to semantic search.
mlops
ML in Production
End-to-end pipelines: training, evaluation, serving, and monitoring ML models in distributed cloud environments.
Tech stack
Tools of the trade.
Languages & Frameworks
- Python
- FastAPI
- PyTorch
- SQLAlchemy
AI / ML
- LLMs
- RAG systems
- Embeddings
- Hugging Face
- OpenAI API
Infrastructure
- Kubernetes
- Docker
- Helm
- Cloud (AWS / GCP)
Systems
- Async Python
- PostgreSQL
- Redis
- Message queues
Contact
Let's connect.
Feel free to reach out if you're building interesting AI systems or just want to talk about applied AI. Find me on: