José Miguel Gómez

A portfolio by

Miguel

Senior AI Engineer / Solutions Architect

In short

I build AI systems that come with evidence: enterprise triage and remediation engines, agentic workflows behind human approval, and tools that reconstruct what happened from the data teams already have. Every production is measured on named hardware, instrumented with OpenTelemetry and audited before release. Cloud models are reached through a gateway so cost, provider and policy stay visible; local-first is the default wherever the data is personal. I work across Python, TypeScript and Java, with LangGraph, MCP, Postgres and Kafka as the usual cast.

Cast of productions

Generated from the catalogue, so these credits never drift from the programme. Each title links to its sheet.

Now showing

  • Enterprise AI system Resolvo draft Autonomous incident triage and remediation with human-in-the-loop
  • Application Before and after Three website redesigns measured with one reproducible audit
  • Game HIT YOUR MARK A 1930s stunt double performs every take, then directs his own cut
  • Developer tool Mirador Every repository at a glance, and what needs your decision today
  • Agentic workflow Specgate draft Approved specs in, reviewed code out
  • Enterprise AI system Tideline draft Turn a flood of support tickets into the one incident that matters

Coming soon

  • Developer tool Aforo One contract and conformance suite for ten polyglot booking APIs
  • Developer tool Kata hexagonal + DDD One game-jam core on REST, GraphQL and PGlite, measured against layers
  • Experiment KataJam frontend katas Micro-frontends and five rendering strategies, each measured against the same tests
  • Application Makora draft Macros. Clarity. Local.
  • Application Revela draft Raw footage to publish-ready reels: planned by AI, rendered on your machine
  • Developer tool Seedworks Same seed, same world in C#, C++ and the browser
  • Application Sublingua draft Live translated subtitles for any call, entirely on your laptop
  • Creative tech Trysac Low-Poly Sampler Every low-poly asset is a seeded Python script for Blender
  • Developer tool Vigilo draft Know what broke, why it matters, and whether it's yours
  • Creative tech XR Showroom Place low-poly assets in your room or walk among them, no app

In production

  • Enterprise AI system Resonar Your social media agency, with you as the only approver
  • Enterprise AI system Veta Mining compliance that goes live in days, not months
  • Agentic workflow Forgeline draft From requirement to reviewed PR, governed end to end

Experience

  • To be confirmed Since to be confirmed To be confirmed To be confirmed

Education

  • To be confirmed To be confirmed To be confirmed

Skills

  • Languages Python, TypeScript, Java
  • Agents and models LangGraph, MCP, LiteLLM gateway, Claude Code, Evaluation harnesses
  • Observability and operations OpenTelemetry, Grafana, Incident management, Human-in-the-loop
  • Data and messaging PostgreSQL, pgvector, Kafka, OpenSearch
  • Delivery Astro, Docker, GitHub Actions, JSON Schema, Spring Boot

Languages

  • To be confirmed To be confirmed

Contact

  • GitHub To be confirmed
  • LinkedIn To be confirmed
  • Email To be confirmed
  • Web To be confirmed