Skip to content
Houssam
EnglishFrançais

Houssam El Ayadi · Data & AI Engineer

From complex systemsto useful products.

I'm a Data & AI engineer and full-stack builder. I design data platforms, retrieval-augmented AI and the APIs and interfaces that make them useful.

See selected workStart a conversation
  • Data engineering
  • RAG & LLMs
  • Automation
  • Full-stack
Scroll to explore

01Capabilities

Four disciplines, one system.

These usually sit in separate teams. My work is connecting them, so data, models and product move together.

  1. 01

    AI systems

    Retrieval-augmented generation and LLM features that are grounded in real data and wired into a product.

    • RAG pipelines
    • Embeddings & vector search
    • LLM integration
    • AI feedback & scoring

    Seen inDocument RAG PipelineAI Content PlatformClinical Training Simulator

  2. 02

    Data platforms

    Pipelines that take high-volume, messy data and make it searchable, analysable and actionable.

    • Log ingestion & parsing
    • Search & aggregation
    • Distributed analysis
    • Dashboards & alerting

    Seen inELK Log Analytics

  3. 03

    Automation

    Multi-step processes with explicit control flow, so behaviour stays predictable when AI is involved.

    • Backend orchestration
    • State machines
    • Evaluation workflows
    • KPI alerting

    Seen inClinical Training SimulatorELK Log Analytics

  4. 04

    Full-stack products

    APIs, persistence and interfaces that turn a pipeline into something people can actually use.

    • FastAPI services
    • Data modelling
    • Application UIs
    • Supabase · MongoDB · PostgreSQL

    Seen inAI Content PlatformClinical Training Simulator

02Services

Select a challenge. See the system take shape.

Five kinds of work I take on, from a first AI feature to modernizing a product that already exists. Each one ends with something your team can run.

  • fig. 01inputs → model → review → output

    Concept illustration: AI Applications & Workflows

    When your team loses hours creating, sorting or searching for information, I build AI features and connected workflows that do the heavy lifting, with a person still in control of what goes out.

    Discuss an AI workflow

    What you get

    1. 1.AI-powered interfaces for generating or processing content
    2. 2.Integrations between language models, your data and your existing tools
    3. 3.Human review steps before anything is published or sent

    Typical tools

    • LLMs
    • RAG
    • FastAPI
    • Python

03Selected work

Systems I've designed and built.

Four projects across GenAI, data platforms and health AI. Each starts with a problem and ends with something people use.

01 — FeaturedGenAI · Content generation

AI Content Platform

content-platform / new brief
Illustration

Brief

Announce a new feature to existing customers. Friendly, concise, one clear call to action.

Context retrieved

  • brand-voice
  • product-notes
  • past-campaigns

Draft

Generating

[1] brand-voice[2] product-notes
  1. FastAPI
  2. RAG / LLM
  3. Store
  4. AI services
  5. Output
Illustration of a brief being turned into generated content using retrieved context.

An AI content platform that turns a user's brief into generated marketing content, grounded in retrieved context.

Problem

Generic prompting produces generic content. Useful output needs the right context retrieved and applied consistently, behind a dependable API.

Approach

  1. 01A FastAPI service receives each request and coordinates the pipeline.
  2. 02Retrieval-augmented generation supplies the language model with relevant context.
  3. 03Supabase and MongoDB persist application data and results.
  4. 04Further AI services process the output before it is returned.
  • Python
  • FastAPI
  • RAG
  • LLMs
  • Supabase
  • MongoDB
logs → index → alert
Illustration

Raw logs

  • 12:04:31INFOapiGET /health 200 4ms
  • 12:04:31WARNworkerretry job=881 attempt=2
  • 12:04:32ERRORapiPOST /checkout 502 184ms
  • 12:04:32INFOauthlogin ok user=•••
  • 12:04:33INFOapiGET /orders 200 21ms
  • 12:04:33ERRORapiPOST /checkout 502 201ms
  • 12:04:34INFOworkerjob=882 done 1.2s
  • 12:04:35WARNdbslow query 840ms
  • 12:04:31INFOapiGET /health 200 4ms
  • 12:04:31WARNworkerretry job=881 attempt=2
  • 12:04:32ERRORapiPOST /checkout 502 184ms
  • 12:04:32INFOauthlogin ok user=•••
  • 12:04:33INFOapiGET /orders 200 21ms
  • 12:04:33ERRORapiPOST /checkout 502 201ms
  • 12:04:34INFOworkerjob=882 done 1.2s
  • 12:04:35WARNdbslow query 840ms

Structured event

{
  "level": "error",
  "service": "api",
  "route": "/checkout",
  "status": 502,
  "latency_ms": 184
}

Alert rule

WHEN
status ≥ 500
RATE
above threshold
THEN
notify on-call

Evaluating

Illustration of raw log lines being parsed into structured documents and evaluated by an alert rule.

02Data platform · Observability

ELK Log Analytics

A log analytics pipeline that turns raw application logs into searchable data, deeper analysis, dashboards and alerts.

  • Logstash
  • Elasticsearch
  • Spark
  • Kibana
query → nearest chunks → answer
Illustration
ChunksVector spaceAnswer
Illustration of documents split into chunks, embedded as vectors, and the nearest chunks retrieved to ground an answer.

03Retrieval · pgvector

Document RAG Pipeline

A retrieval-augmented generation pipeline that answers questions from a document collection using vector search in PostgreSQL.

  • PostgreSQL
  • pgvector
  • Embeddings
  • LLMs
clinical-sim / session loop
Illustration
Illustration of a training session loop: student action, state transition, clinical evaluation and AI feedback, producing a score.

04Health AI · Clinical training

Clinical Training Simulator

A clinical training application where students work through cases, guided by a state machine and evaluated with AI feedback and scoring.

Clinical training needs structure: cases must move through controlled steps and feedback must be consistent. An open-ended chat is not enough.

  • Orchestration
  • State machine
  • Clinical engine
  • LLMs

04Inside the systems

How data becomes a product.

The architecture behind each project, step by step. Select a node, or use the arrow keys, to see what each part is responsible for.

An AI content platform that turns a user's brief into generated marketing content, grounded in retrieved context.

Full AI Content Platform case study →

  1. A user describes the content they need.

05How I work

From question to running system.

  1. 01

    Discovery

    Understand the problem, the people involved and the data that exists before choosing any tools.

    What comes out

    • Problem framing
    • Data inventory
    • Success criteria

  2. 02

    Architecture

    Design the flow end to end: sources, processing, storage, intelligence and the interfaces on top.

    What comes out

    • System diagram
    • Data model
    • Explicit trade-offs

  3. 03

    Build

    Ship in thin vertical slices, so pipeline, API and interface grow together and stay testable.

    What comes out

    • Pipelines & services
    • Typed APIs
    • Working interface

  4. 04

    Validation

    Check data quality, retrieval and model behaviour, and how the system fails, not just how it succeeds.

    What comes out

    • Test cases
    • Evaluation checks
    • Failure handling

  5. 05

    Delivery

    Deploy, observe and hand over something a team can understand and operate.

    What comes out

    • Deployment
    • Dashboards & alerts
    • Documentation

—Principles

  1. 01

    AI is a system, not a prompt.

    Models sit inside data, evaluation, serving and monitoring. I design the whole loop.

  2. 02

    Data quality comes before intelligence.

    Retrieval and outcomes are only as good as the data and structure underneath.

  3. 03

    Automation should remove friction.

    Pipelines and workflows should make teams faster, not create new manual work.

  4. 04

    Production matters more than prototypes.

    Latency, cost, failure modes and observability decide whether it is a demo or a product.

06Technology

A stack, organised by what it does.

Tools grouped by their role in a system, from the layer people touch down to where data lives. Pick a project to see how its stack fits together.

  1. Interfaces & APIs

    Where systems meet people and other software.

    • FastAPIUsed in AI Content Platform
    • KibanaUsed in ELK Log Analytics
    • Next.js · ReactThis site

  2. Intelligence

    Models and retrieval that turn data into answers and feedback.

    • LLMsUsed in AI Content Platform, Document RAG Pipeline, Clinical Training Simulator
    • RAGUsed in AI Content Platform, Document RAG Pipeline
    • EmbeddingsUsed in Document RAG Pipeline
    • AI feedback & scoringUsed in Clinical Training Simulator

  3. Orchestration

    Control flow that keeps multi-step processes predictable.

    • Backend orchestrationUsed in Clinical Training Simulator
    • State machinesUsed in Clinical Training Simulator
    • KPI alertingUsed in ELK Log Analytics

  4. Processing

    Pipelines that clean, transform and analyse data.

    • LogstashUsed in ELK Log Analytics
    • SparkUsed in ELK Log Analytics
    • Document chunkingUsed in Document RAG Pipeline

  5. Data & storage

    Stores chosen for how the data is queried.

    • PostgreSQLUsed in Document RAG Pipeline
    • pgvectorUsed in Document RAG Pipeline
    • ElasticsearchUsed in ELK Log Analytics
    • SupabaseUsed in AI Content Platform
    • MongoDBUsed in AI Content Platform

Languages: Python · SQL · TypeScript

07Contact

Have a system worth building?

I'm open to Data & AI engineering roles and project work: data platforms, RAG and LLM features, automation and full-stack products. Tell me about the problem.