Skip to content
02 · ABOUT

I build AI systems that run at scale. And I document everything.

I'm Cristhian Fonseca — a Technical Lead with 5+ years building cloud-native FinTech and banking platforms.

Technology serves the business, not the other way around. I build what moves the metric, not what looks good in the codebase.

Right now I lead engineering for a digital credit marketplace inside a major telecom's Super App — ~100K monthly active users within a 45M-user ecosystem. Cloud-native on AWS, automated provisioning, zero-paperwork loans.

I specialize in agentic AI systems — MCP agents, multi-step LLM pipelines, and automation architectures that handle real data volumes with real cost constraints. Every system I publish is first deployed in production.

I believe the best engineers don't just write code — they build systems that compound. And they share what they learn.

EXPERIENCE
  1. May 2025 – Present

    Technical Lead · Prosperas

    Credit marketplace inside a major telecom's Super App

  2. Nov 2024 – Mar 2025

    Lead Developer · ImkGlobal (Ingenieros de Marketing)

    Apps for government-backed regional tourism services

  3. Oct 2022 – Aug 2026

    Full-Stack Developer (Frontend consulting) · eSoluzion

    Core banking modules for an enterprise banking client

  4. Apr 2022 – Mar 2023

    Software Engineer · Dualboot Partners

    Cloud services for a US-based car-rental platform

  5. May 2021 – Jun 2022

    Data Analyst / Java Developer / Full-Stack Developer · Accenture

    A global bank's Colombian operation and a telecom operator

  6. Feb 2026

    Claude Code in Action

    Anthropic

CORE STACK

AI & agents

Claude API, Claude Code (skills, headless, sub-agents, hooks), MCP servers, LLM routing (OpenRouter), pgvector / RAG, agent memory, adversarial review agents, spec-driven development (OpenSpec)

Cloud & infra

AWS CDK, ECS Fargate, Lambda, RDS/PostgreSQL (gp3, Graviton), ElastiCache/Redis, S3, CloudFront, WAF, SQS, Route 53, Cognito, Secrets Manager, CloudWatch, Cost Explorer/Budgets, Terraform, Docker, Caddy, Cloudflare

Backend

Python, FastAPI, SQLAlchemy, Alembic, Celery, sqlglot, Java, Spring Boot, Node.js, TypeScript

Frontend

Angular, ECharts, SvelteKit, Next.js, Thymeleaf, Flutter

Data

PostgreSQL (materialized views, COPY, locking, partial indexes), MySQL, Oracle, MongoDB, Power BI

Observability

Sentry, CloudWatch alarms, synthetic probes

WHY I BUILD IN PUBLIC

Most engineers keep their best architecture decisions private. I think that's backwards. When I ship something that works, I document it and publish it. The community makes me better.

This isn't hypothetical. Every automation template in PowerAI was first deployed in a real system. Every architecture diagram was drawn after the code ran in production.

If you're building with AI, I want to hear what you're solving. The best ideas in this newsletter come from conversations with engineers who are actually shipping.

EDUCATION & CERTIFICATIONS
B.Eng. Systems Engineering·Universidad Autónoma de Bucaramanga (UNAB) · 2016 – 2020Technical Degree in Computer Systems·SENA · 2014 – 2016Claude Code in Action·Anthropic · Feb 2026AWS Partner: Accreditation (Technical)·Amazon Web Services · Jul 2020Neural Networks and Deep Learning·deeplearning.ai / Coursera · Sep 2020

Building with AI at scale? Let's connect.

Hiring for a remote Technical Lead? Email me. Founders and CTOs shipping with AI, say hello too.