Résumé
Sebastian Ramos Regalado
Staff AI Engineer · Full-stack systems, cloud and data
A quick record of the software, cloud, data and applied AI systems I build, plus how I lead and what I studied.
Based in Quito, Ecuador (UTC−5). Open to remote opportunities worldwide and relocation, with flexible time-zone availability.
sramosre@gmail.com · linkedin.com/in/sebastian-ramos16
Roles
- Staff Engineer, Capmation
- 2020 – Present · Remote from Quito, Ecuador · Capmation is based in the Twin Cities, MN, US
- I design and deliver production AI and software systems, from the first technical direction through implementation, deployment and the improvements after. The work covers agentic AI, RAG, backend services, cloud delivery, data infrastructure, and the engineering practices that keep those systems dependable.
- My AI work sits inside real business processes: LLM-powered applications and workflows wired into the APIs and databases a team already depends on.
- When I design multi-step agents, retrieval pipelines and automation, I set clear tool boundaries up front so each piece has an owner once it's running.
- The Python and .NET backend services behind those systems also handle real-time data processing, and I deploy them across Google Cloud, AWS and Azure.
- Vertex AI, Docker, Kubernetes and CI/CD are how I carry models and services from development into production at scale.
- I work directly with cross-functional teams to turn business needs into systems we can ship, while leading delivery and mentoring engineers.
Team leadership
I lead from inside the code. I've run teams of up to 5 engineers and mentored 6, and I've watched several of them grow into more confident, independent engineers. I own the architecture and the delivery, and I make the technical calls clear enough that the team can move fast without second-guessing them.
Expertise
Grouped by the engineering problem each one helps solve.
Applied AI & LLM systems
Building useful LLM features around context, retrieval, and product workflows.
- OpenAI API
- Anthropic Claude
- LangChain
- LangGraph
- CrewAI
- AutoGen
- RAG
- prompt engineering
- embeddings
- semantic search
Agent systems, evaluation & reliability
Making autonomous systems observable, bounded, and safe to improve.
- MCP (Model Context Protocol) servers
- custom tools & sub-agents
- tool-using agents
- multi-agent architectures
- memory & context management
- autonomy boundaries & guardrails
- AI orchestration
- autonomous workflow execution
- offline eval sets
- LLM-as-judge
- human calibration
- CI regression gates
- tracing & tool-call logs
- cost & latency budgets
- LangSmith / Langfuse
Machine learning & computer vision
Applying practical ML, deep learning, NLP, and vision to real systems.
- PyTorch
- TensorFlow
- scikit-learn
- deep learning (MLPs, CNNs)
- NLP
- feature engineering
- model optimization
MLOps, cloud & platform delivery
Moving models from experiment to monitored, repeatable production delivery.
- Docker
- Kubernetes
- CI/CD pipelines
- MLflow
- model versioning
- Terraform
- microservices
- Vertex AI Pipelines
- Airflow
- Kubeflow
- batch & real-time serving
- AWS
- Azure
- Google Cloud (Vertex AI)
Data engineering & retrieval
Designing reliable data paths across analytics, operational, and vector systems.
- Microsoft Fabric
- Databricks
- Medallion architecture
- Power BI
- ETL / ELT
- Pinecone
- Weaviate
- FAISS
- PostgreSQL
- MySQL
- SQL Server
- MongoDB
Software engineering & integration
The services, interfaces, workflows, and languages around the AI layer.
- n8n
- Zapier
- Make
- REST APIs
- webhooks
- event-driven systems
- internal tools & admin UIs
- Python
- SQL
- Bash
- TypeScript / JavaScript
- C#
- .NET
- Java
Education
- LaSalle College · Program in Artificial Intelligence & Machine Learning · Montreal, Canada (2024–2025)
- Universidad San Francisco de Quito · B.Sc. in Computer Engineering · Quito, Ecuador (2014–2020)
Languages
English (native), Spanish (native)