I enjoy building AI systems that are useful, reliable, and grounded in real problems. My work sits at the intersection of research, engineering, and product, spanning retrieval pipelines, document intelligence, production ML, evaluation, and cloud-native deployment.
I enjoy collaborating with people who want to turn good ideas into real systems, especially in applied AI, knowledge systems, NLP, and data-intensive products.
| Dimension | Snapshot |
|---|---|
| Foundation | Computer Science + Mathematics at Universidad Nacional de Colombia, with a 4.7/5.0 GPA |
| Approach | I like taking ideas from papers and prototypes to production-ready systems |
| Range | I have worked across research, healthcare, retail, market research, and financial knowledge systems |
| Current growth | I am pursuing an M.S. in Artificial Intelligence at Universidad de los Andes |
I like building systems that move from ideas to real impact.
flowchart LR
A[Mathematics and Research] --> B[Models and Evaluation]
B --> C[Systems and Infrastructure]
C --> D[Production AI Products]
D --> E[Useful Real-World Outcomes]
| Area | What it means in practice |
|---|---|
| Knowledge Systems | Retrieval, ranking, grounding, and structure over complex information |
| AI Products | Combining models, software engineering, and good judgment under real constraints |
| Machine Learning | Prediction, NLP, deep learning, decision-oriented systems, and practical evaluation |
| Learning Systems | Reinforcement learning, multi-agent reasoning, and research-driven experimentation |
| Open Source | Model implementation, practical tooling, and agent ecosystems such as OpenClaw |
| Cloud-Native AI | Observable, testable pipelines built to evolve rather than break |
I am especially interested in projects where AI has to be both technically strong and operationally useful: document understanding, retrieval over complex knowledge, evaluation of LLM systems, human-in-the-loop workflows, and the infrastructure that makes them dependable.
Background
Over the last few years, I have worked on a wide range of AI problems: predictive systems, NLP pipelines, computer vision, deep learning models, retrieval and document intelligence, reinforcement learning experiments, multi-agent environments, and production ML infrastructure. I have contributed across research settings, enterprise contexts, healthcare applications, retail operations, and open-source projects.
That range matters to me because I do not see AI as a narrow specialty, but as a broad engineering and scientific field where modeling, systems thinking, and implementation all matter. I am most energized by problems that require both technical depth and the willingness to build something real.