Julián Cardozo · Engineering Manager

I lead engineering teams.

15+ years in software: I started in Java backends, grew through banking and fintech working on payments, and today I lead cross-functional teams across architecture, platform and delivery. My code is still public, so you can review it before we talk.

Open to my next opportunity as an Engineering Manager.

15+
years in software, from developer to Engineering Manager
10
products of my own with a case study
7
live today
50
public repositories on GitHub

Programming with AI agents

A framework so AI agents speed up the team

Programming with agents isn't asking a chat for code. It's designing the system they work in. To bring them into the development cycle I use four layers:

  1. Specification

    With spec-driven development, every change starts from what it has to do, what can't break and how we are going to verify it.

  2. Context

    Repository rules, architecture decisions and close examples are versioned in files like AGENTS.md, so any agent works with the same judgment as the team.

  3. Harness

    Scoped tasks, tools connected through MCP and automated checks (tests, linters, evals) that validate every result.

  4. Human review

    The team decides what gets merged and what we can maintain. The riskier the task, the more control it gets.

The time we get back is reinvested in what an agent can't solve: understanding the problem with product, testing the critical cases and making design decisions that last for years.

  • Spec-driven development
  • Context engineering
  • Agent harness
  • MCP
  • Evals
  • Human-in-the-loop
  • Claude Code
  • Cursor
  • Kiro

Strengths

What I bring to an engineering team

Six strengths, each with a place where you can check it.

Team leadership

Cross-functional teams, priorities, mentoring and the conversation with the business. I want teams that deliver steadily without relying on heroes.

Product and business

I start from the problem, not the stack. I translate trade-offs between engineering and the business, and I can take an idea from zero to production.

Close to the code

I lead without losing technical judgment. I keep building in Java, TypeScript and Python, all of it in the open.

Career

From building systems to leading engineering teams

Each stage widened the system I was responsible for and left me with a capability I still use.

  1. Today

    Engineering Manager

    I lead cross-functional teams: architecture, platform, priorities and the conversation with the business. Less of my own code and more decisions that enable other people’s code.

    Capability gainedTechnical strategy, mentoring and translating between engineering and business.

  2. Alongside

    My own products and artificial intelligence

    Spec-driven development, AI-assisted development, agents and MCP applied to the whole cycle. AI doesn't replace judgment: it compresses the time between understanding a problem and having something working.

    Capability gainedGoing from need to deployed product without depending on a whole team.

  3. Agency and clients

    Product, design and communication

    I founded and worked in a development and digital marketing agency: websites, e-commerce, branding and complete deliveries for real clients, with a budget and a deadline.

    Capability gainedSelling, designing and communicating a solution, not just building it.

  4. Fintech

    Scale, integration and speed

    Volume, third-party integrations, webhooks, observability and short delivery cycles without lowering the security bar.

    Capability gainedDesigning for integration: every real system lives alongside others you don't control.

  5. Banking and payments

    Transactions, security and regulation

    I worked where money actually moves: reconciliation, payment states, auditing, access control and regulatory requirements that are not negotiable.

    Capability gainedUnderstanding a payment as an auditable state machine, not an HTTP call.

  6. Early years

    Java developer

    Backend, REST APIs, Spring, persistence, message queues. Enterprise systems where an error isn't a cosmetic bug: it's a transaction that never happened.

    Capability gainedSolid backend skills and respect for data consistency.

  7. Foundations

    Computer science and software engineering

    Algorithms, data structures, databases and design patterns. The part that doesn't expire: when a system goes down at three in the morning, what helps is understanding what's happening underneath.

    Capability gainedJudgment to reason about systems, not just use them.

How I lead

Four principles I bring to every team

Context over micromanagement

A team decides well when it understands the problem and its constraints. My job is to create that context, not to make every decision.

Teams that don't depend on heroes

If something only works when one person is around, it isn't solved yet. I aim for shared knowledge and sustainable delivery.

Architecture follows the business

Multi-tenancy, dual currency or an event ledger are business decisions written in code, and they're expensive if they arrive late.

AI amplifies judgment; it does not replace it

It speeds up researching, specifying and building. Deciding what gets built, reviewing what it produces and owning the result stays with people.

Projects

Some of my digital products

Alongside leading, I build my own products end to end. Every case study shows the problem, the technical decisions and the real status.

More case studies

Capabilities

Skills and stack

From managing the team to running in production.

Lead

Teams that deliver without depending on a single person.

  • Technical strategy
  • Team management
  • Prioritization
  • Mentoring
  • Engineering culture
  • Partnering with the business

Discover

Find the real problem before writing code.

  • User research
  • Product discovery
  • Hypothesis validation
  • Market analysis
  • Scope definition

Design

Translate the problem into a model that holds up.

  • Domain modeling
  • Solution architecture
  • API design
  • UX/UI
  • Executable specifications

Build

End-to-end product, from data schema to deploy.

  • Java / Spring Boot
  • Node.js / NestJS
  • React / Next.js / Angular
  • PostgreSQL / MongoDB
  • Integrations and payments

Operate

Keep it running when you're no longer watching it.

  • Docker / Kubernetes
  • CI/CD
  • AWS and cloud
  • Observability
  • DevSecOps
  • Infrastructure as Code

Accelerate with AI

Use AI across the whole cycle, with judgment and verification.

  • Spec-driven development
  • AI-assisted development
  • Agents and MCP
  • Rapid prototyping
  • Lifecycle automation

Pillars

How I think, in writing

Articles and projects grouped by theme: engineering with AI, technical leadership, architecture and product.

Pillar

Engineering with AI and agents

How to bring AI agents into the development cycle: specification, context, a control harness and human review.

Pillar

Technical leadership and teams

How I think about technical leadership, autonomy, sustainable delivery and the relationship between engineering, product and business.

Pillar

Products, startups and MVPs

From observing the problem to the MVP: onboarding, user experience, hypotheses, validation and designing sustainable solutions.

Contact

Let's talk about your team

Looking for an Engineering Manager or putting an engineering team together? Write to me. I answer every message.

  • Engineering leadership and team management
  • Fintech, payments and regulated systems
  • Platforms, integrations and backend architecture
  • Adopting AI in the development lifecycle