Diego Castronuovo

Agentic AI Platform Engineer · AI agents for infrastructure operations and software delivery

Email: info@diegocastronuovo.com

Geneva, Switzerland (available remotely)

About Me

I design, build and run production AI agent systems. At Sporfie I built the agent platform a small engineering team now works through every day: it investigates production incidents with evidence, runs operations behind human approval, designs and plans features, reviews every pull request, and delegates whole epics to coding agents running in the cloud. It is the same class of product as TierZero (now Cognition) or Resolve.ai, built in-house on AWS Bedrock and MCP, and shipped essentially by one engineer.

Those agents sit on the production platform I built from scratch and have run for ten years at Sporfie, from Kubernetes and GitOps to GPU workloads and CDN. I know how production breaks, which is why my agents are read-only by default, fail-closed on tools, audited on every call, and gated by an approval app with no AI in it.

I go full-stack when it speeds delivery. Since 2016 I have also partnered with founders around Geneva as a consultant and fractional CTO. I am open to senior, staff or founding roles where agentic engineering and platform depth compound.

Languages: Italian (native), English, Spanish and French (full professional). Finalist, PostFinance Digital Business Award 2015.

Experience

Sporfie

https://sporfie.com

AI Platform, Full Stack & DevOps Architect

Feb 2016 - Present

Since 2025: from LLM-assisted debugging of production issues to an agentic AI platform, designed and shipped in 2026 and live in production. It has two halves: Sporfie Agents, where the team investigates and operates, and CodeDev, where coding agents build.

Sporfie Agents (Python / FastAPI, AWS Bedrock, MCP): a multi-agent system for investigation and operations. An LLM router sends each question to one of five specialist agents (infrastructure, operations, design, development, tech lead), each a persona with a fail-closed tool allowlist and its own case memory. 19 read-only MCP servers over Kubernetes, CloudWatch, Prometheus, GitHub, SQL, Jira and more; any change goes through a signed plan, a human approval in an AI-free app and a separate executor, with a full audit trail. Reachable from the web, Slack, Claude Desktop (MCP) and GitHub, where a Tech Lead agent reviews every PR. One LiteLLM gateway gives each agent a key, a budget and a cost per conversation; a regression eval suite gates releases.

CodeDev (TypeScript / Node, React, Kubernetes): a cloud workstation where Claude Code (Agent SDK), Codex and OpenCode build and run the real stack and hand back a branch, a PR and a verified preview URL. Per-branch preview environments, an epic mode that runs parallel agents in git worktrees against a server-checked definition of done, deterministic commit and push guards as hooks, and an MCP so other agents can delegate coding work.

Platform and back end (2016 onward): building and running the platform end-to-end since day one of this live-streaming SaaS. Led the move to Kubernetes in 2020 with a strong GitOps + IaC culture; introduced Karpenter for smarter autoscaling, built a Kubernetes-native serverless framework to bypass Lambda limits, and run GPU workloads for streaming and AI tooling.

Own multiple back-end services (Java/Go/Python/Node), lead performance and scalability work, create load-testing suites, and implement multi-layer caching (including CloudFront for less-dynamic public APIs). Hands-on with CDN architecture and operations: cache strategy, invalidation, edge behavior, origin design, and the observability needed to troubleshoot real-world delivery issues.

Stack: Kubernetes, ArgoCD, Karpenter, Prometheus, Grafana, Docker, PostgreSQL, Java / Spring Boot, Node.js, Python (OpenCV, FFmpeg), Go, Firebase, GraphQL, REST, Redis / Redisson, HAProxy, CircleCI. AWS: Lambda, CloudFront, S3, ElasticTranscoder, CloudWatch. AI: AWS Bedrock, MCP, Claude Agent SDK, LiteLLM, Python / FastAPI.

Generali Insurance

https://www.generali.ch/en/

DevOps Architect

Sept 2018 - Dec 2019

Freelance consultant on a private cloud solution with OpenShift (Kubernetes), Docker and Kafka. Helped drive GitOps practices during the Kubernetes migration.

  • CI/CD refactor using a GitOps approach
  • Monitoring infrastructure (Prometheus and Grafana)
  • Namespace quota management
  • Docker image security scan set up with Anchore Engine

Freelance

Software Engineer / Entrepreneur

Oct 2015 - Dec 2018

Lean startup experiments with cloud deployment and high-productivity tools (Java 8, Spring Boot, AWS, Firebase, GraphQL, REST, Elasticsearch, Docker, CircleCI, serverless and microservices architectures, Spring Data, MySQL).

Hortis GRC SA

https://www.hortis.ch

Java Consultant

Nov 2014 - Oct 2015

Back-end Java development of GlassIG, a SaaS for corporate information governance. Involved in the migration from on-premise infrastructure to the cloud.

  • Coaching the dev team (talks on unit/integration tests and Java common libraries)
  • DSL for integration test automation
  • Application security and code quality (Veracode, SonarQube)
  • Configuration versioning system based on Zookeeper and XSLT
  • Maven multi-module refactoring; Spring config refactor (XML to Java-based)
  • Refactoring of legacy code

Stack: Spring, Hibernate, Maven, TDD, Zookeeper, AWS, Tomcat, Vagrant, Hazelcast, Jenkins, JIRA.

Swissquote Bank SA

https://www.swissquote.ch

Development Engineer

Jul 2011 - Aug 2013

Development and maintenance of back-end batches and daemons (80%) and web applications (20%):

  • Cash management (incoming and outgoing payments)
  • Interface between the front (Swissquote platform) and back-end (Temenos T24 banking package)
  • Documents automation: report generation and spooling

Stack: Java, Spring, Hibernate, Maven, Mercurial, TDD, JUnit, Concordion, jBehave, Spring Integration, JMS, SOAP/Axis, Stripes, Resin, Flex, ANSI C, Bash, Perl, HP Dialogue, Scala, Oracle DB, SQL, Atomikos, Quartz, jQuery, Scrum/Kanban, Jira, Confluence, Hudson/Jenkins, Linux & Solaris.

Skills

Agentic AI: multi-agent orchestration, LLM routing, sub-agents, tool use, MCP (servers, clients, MCP Apps), Claude Agent SDK, Claude Code hooks and skills, Codex, OpenCode, AWS Bedrock, prompt caching, evals, LLM gateway (LiteLLM) and cost control, guardrails (fail-closed allowlists, least privilege, human-in-the-loop approval, audit trails), semantic memory (pgvector), AI SRE and incident response agents, Slack bots, GitHub webhooks.

Platform: Kubernetes (EKS), ArgoCD and GitOps, Karpenter, Terraform, Helm, site reliability (SRE), on-call and incident response, observability with Prometheus, Grafana and CloudWatch, Athena, Docker and BuildKit, PostgreSQL, Redis, CircleCI, oauth2-proxy and SSO, Vercel, CDN operations.

Languages: Python (FastAPI), TypeScript and Node (React, Vite), Java (Spring Boot), Go, SQL, Bash.

Education

Università di Bologna - Bologna, Italy

2007 - 2011

Master’s Degree in Computer Science

Università di Bologna - Bologna, Italy

2004 - 2007

Bachelor’s Degree in Internet Sciences

Liceo Scientifico Aldo Moro - Reggio Emilia, Italy

Scientific high school

A Little More About Me

Alongside my interests in software engineering some of my other interests and hobbies are:

  • Being a father
  • Cooking
  • Travelling