Everything here is running. No screenshots-only exhibits: each one links to something you can execute, read, or query.
ex. 01
mdingest
live
Turns blog articles and newsletters into clean Markdown for LLMs. One ingestion core behind four entry points: HTTP API, CLI, and an MCP server over stdio + HTTP.
live on cloudflare · 4 entry points · mcp + llms.txt ready
> calls the production api at mdingest.knightker.workers.dev — real article in, markdown out. the url is yours to change.
ex. 02
italki-cli
live
italki has no official API, so I built one from the outside: a Zod-validated CLI + MCP server to search, compare, and book lessons, with layered architecture enforced by custom lint rules.
Found 645 english teachers (type=pro, max=$20.00, native) #32651986 Ethan M [PRO] from US — from $16.00★5 20 sessions trial $10.00 #4611201 Matt [PRO] from GB — from $15.00 new trial $8.00 #1084019 Lewella [PRO] from US — from $20.00★5 20178 sessions trial $5.00 #855323 Teacher Jong [PRO] from PH — from $12.00★5 19581 sessions trial $5.00 #953117 Regina Esther [PRO] from PH — from $12.00★5 9819 sessions trial $8.00 Next page: italki search english --type pro --max-price 20 --native --page 2 View profile: italki teacher <id>
captured sep 28 — 645 real matches, real teachers, real prices
What happens when someone clicks a button in one of my apps. Left to right: the visitor's browser, the edge, the API, the database.
live render · request anatomyrunning
click in the browser → edge → api → lands in postgres.
The record
TXEN
AI Engineer
dec 2025 · present
~150ms
selector load time, down from 5-8s
Software consultancy. Full-stack engineer on Péntica (B2B SaaS for municipal tax compliance across Colombia's 1,103 municipalities), then AI Engineer on Doru (AI clinical-records SaaS for veterinary clinics).
Engineered Doru's AI consultation-to-clinical-record pipeline (speech-to-text, LLM structured extraction, Pydantic schema validation with automatic retries, and veterinarian human-in-the-loop review before records are saved); owned its event-driven automated reminders, AWS infrastructure, and React frontend optimizations.
Built a hybrid RAG service in Python and FastAPI over Colombian tax regulations for accountant lookup: keyword + pgvector retrieval fused with RRF, article-aware chunking preserving each regulation's hierarchy, cross-encoder reranking, exact citations to the regulation, superseded-norm detection, and deterministic abstention on out-of-corpus or superseded norms — validated against a golden dataset curated by the accounting team.
Cut company-selector load time from 5-8s to ~150ms across 14 frontend modules by designing a lightweight endpoint returning only required fields (replacing ~150K-line JSON responses), measured via CloudWatch.
Designed and executed a 19-phase PostgreSQL migration (Simplica → Péntica): schema mapping across differing names and types, idempotent re-runs via natural-key deduplication, dry-run mode, and per-municipality validation.
Implemented continuous production reverse sync from Péntica back to Simplica via SQS, and automated the ICA tax-matrix update workflow (replacing manual email dispatches and hand-attached normativity files).
Migrated production to a new AWS account in under 12 hours (RDS snapshot + S3 sync), configured RDS Proxy + Lambda init-phase TypeORM loading to cut cold starts, and reduced 3,400 ESLint warnings to zero with Prettier across the team.
Promoted from Junior inside a year on a real-time reservation and streaming platform.
Delivered backend work on a real-time reservation and streaming platform in Scala + Kafka, under a senior lead's direction.
Reviewed code and assigned tasks for two junior developers, supporting their delivery.
ScalaKafkaWebSocketsTypeScriptNode.jsPython
↑ promoted
Junior Software Engineer
jan 2024 · dec 2024
100+
endpoints migrated off Node 14
First role. Migrated a lending platform's backend off end-of-life Node 14.
Migrated 100+ endpoints (Node.js/TypeScript on AWS Lambda): built the unit + integration test foundation around business-critical endpoints, deployed to production.
Earned the promotion on code quality, autonomy, and consistent delivery.
TypeScriptNode.jsPythonReactAWS AmplifyAWS Lambda
No Country
Frontend Developer (Intern)
jun 2023 · sep 2023
2
project builds during internship
Project-based internship: real team deliverables on two LATAM community builds.
Urban Move (urban mobility): responsive UIs in React, TypeScript, Tailwind CSS, Vite; frontend testing with Vitest.
UVA (developer-project matching): frontend in React, Vite; code quality via ESLint + Prettier.
ReactTypeScriptTailwind CSSViteVitest
Field notes
Short technical essays on things I actually shipped. Being written now.
Migrating an ingestion API off Containers to pure Workers
the mdingest deploy, honestly
drafting
Why vector-only RAG fails on municipal tax statutes
hybrid retrieval, citations, and abstention — lessons from Péntica work, in Python
“Luis showed strong technical judgment building with AI-assisted tools — he's always at the leading edge. His professional ethics and his ability to communicate across teams and with clients stand out.”
“One of the best developers I know. Before implementing anything he evaluates the options, understands the context, and makes informed decisions. I'd recommend him to any team, remote included.”
“High technical ability and excellent problem-solving skills, with real commitment to the quality of the work. Responsible, proactive, with strong professional ethics.”
“Across Next.js, AWS Lambda, TanStack and DynamoDB he showed real capacity for technical challenges, and proposed solutions oriented to what the project actually needed.”
Every page in this dossier also exists as structured data. Agents and recruiters read the same truth:/v1/me.json, /v1/projects.json, llms.txt, openapi.json, .well-known/ai-catalog.json. And it is callable, not just readable:POST /v1/mcp — this dossier is itself an MCP server.