AI Engineer · Malang, Indonesia (UTC+7)

Daffa Izzuddin

I take models from a training run to something people can actually use: train, serve, monitor, iterate.

Status
Open to AI engineering roles, remote and full time
Currently

Lead Developer, RAINS Corp

Full-Stack AI Engineer, Mayfeyr

Based in
Malang, Indonesia (UTC+7)

I am an AI engineer who likes the unglamorous half of machine learning: getting a model out of the notebook, putting it behind a real endpoint, watching what it does to real users, and then going back to improve it.

Four years in, most of that work sits where ML meets web: image generation for batik patterns, computer vision on satellite imagery, face embeddings for authentication, an autonomous agent that sits on top of clinical paperwork, and the Nuxt/Go/Postgres plumbing that makes all of it usable. Right now that means leading development at RAINS Corp and building the e-commerce and AI stack at Mayfeyr, a multi-brand luxury fashion retailer whose catalogue pipeline I designed and still own.

The research half is not a separate track. My GenBatik work is a first-author paper in IEEE Access (Q1), the framework holds registered IP, and I review for the journal now. I also write about the engineering side at invasikode.com, because explaining a system is a good test of whether I actually understand it.

Experience

Roles, dates, and the systems I owned
  1. Lead Developer

    RAINS Corp

    2026-07 to present · Remote · Founding team

    An autonomous AI agent that runs alongside clinical and administrative staff and writes the activity reports they would otherwise write by hand.

    • Architected and deployed an autonomous shadow agent that now runs alongside clinical and administrative staff, across physician, healthcare worker and front-office roles.
    • Built the inter-agent query routing that holds a 92% query success rate, and I am benchmarking latency against a sub-5s target.
    • Lead a squad of 2 engineers, ship to staging through CI/CD every day, and steer sprints toward 70%+ milestone completion.
    • Own the outward-facing half of the job too: demo the agent to investors, run the weekly sync and sprint sessions, and open pilot conversations with partner organisations.
    • Shipped the production platform at rainscorp.id and the custom GPT apps that give the agent a natural-language front door.

    The agent runs alongside a person's day instead of asking them to change it: it logs the workflow, drafts the report, and the person corrects what it got wrong. The corrections matter, because the agent only earns its place once someone trusts the output enough to stop writing it twice.

    python, typescript, nuxt, postgresql, docker

  2. Full-Stack AI Engineer

    Mayfeyr

    2024-12 to present · Remote · Full-time

    Catalogue ingestion, pricing, storefront content, and the AI features on top of them for a multi-brand luxury fashion retailer.

    • Rebuilt catalogue ingestion as a distributed pipeline in Python and RabbitMQ, sized so that onboarding a large supplier catalogue and the daily price sync both run without losing work.
    • Integrated external supplier APIs behind strict retry queues, so a failed sync retries instead of surfacing as a stale price or a negative-margin order.
    • Refactored the pricing engine around DataLoader batching and cut per-product pricing from 100ms to 10ms, a 10x throughput gain.
    • Pulled the hot paths out into Go microservices (pricing, image caching, content generation, PDF rendering) and moved the rest of the background work onto Celery and n8n.
    • Built Mayfeyr Mirror, the virtual try-on engine, from zero to one, plus custom ChatGPT apps that take a conversational shopping query straight to a product.

    I also own the multi-server infrastructure and the technical SEO/GEO work that got the full catalogue indexed and crawling cleanly.

    python, go, rabbitmq, postgresql, celery, docker

  3. B.Sc. Computer Science

    Universitas Brawijaya

    2021 to 2025 · Education · Malang, Indonesia

    Faculty valedictorian, 3.95/4.00 GPA, degree finished in 3.5 years.

    • First author on a Q1 IEEE Access paper for GenBatik, with registered intellectual property and an open-source implementation.
    • Team lead on the Bangkit Academy capstone with Solafune Japan, ranked #1 in the company track and #1 overall across the academy, graduated with distinction.
    • Lab assistant for two years, teaching basic programming, data structures and algorithms, and computer networking at basic and advanced level.
    • Computer vision lab work on retinal blood vessel segmentation and historical manuscript text recognition.

Projects

Each card opens the build notes

Skills

The four stages I own, each tied to something I shipped
01

Data & Modeling

Framing the problem, cleaning the data, training and evaluating a model I can defend.

  • Dataset preparation and label sanity checks
  • Fine-tuning diffusion models (LoRA / SDXL)GenBatik
  • CNN / embedding models for visionSPARSE, IdentifEye
  • Evaluation beyond a single accuracy numberSPARSE
PyTorch Hugging Face Python NumPy
02

Serving & Inference

A model that only runs in a notebook is not a feature. I put it behind an endpoint and keep it honest.

  • REST / async job APIs around model inferenceGenBatik, IdentifEye
  • Streaming progress to the client (WebSocket)GenBatik
  • Containerised deploy, GPU vs CPU trade-offsSPARSE
  • Latency and cost per requestGenBatik, Mayfeyr
  • Message queues and retry policies that survive supplier failures
  • Batch loading to cut per-product work (DataLoader, 100ms to 10ms)Mayfeyr
  • Microservice extraction when one module gets hotMayfeyr
FastAPI Go Docker Cloudflare
03

Monitoring & Iteration

The part most portfolios skip. I care about what happens after deploy: what broke, what drifted, and what the next version should change.

  • Logging inputs/outputs to make failures reproducibleGenBatik
  • Feedback capture (accepted vs rejected output)TataKata
  • Cost and usage tracking per feature
  • Versioned experiments instead of one-off notebooks
  • Success rate and latency targets measured, not assumedRains, 92% query success
  • CI/CD to staging as the daily default, not a release eventRains
Postgres Grafana GitHub Actions
04

Product Delivery

An AI feature is only as good as the interface around it. I build that part too.

  • Nuxt / Vue front ends for data-heavy productsGenBatik, invasikode.com
  • API design and schema work in Postgres
  • AI features wired into an existing commerce stackMayfeyr Mirror, custom GPT apps
  • Multi-server infrastructure and technical SEO/GEOMayfeyr
  • Static-first builds, prerender, and deploy pipelinesPortfolio (this site)
  • Technical writing that explains a system to non-authorsinvasikode.com
  • Demoing a working system to investors, and partner conversations for pilotsRains
  • Running sprint planning and team sync sessionsRains
Nuxt TypeScript Tailwind Postgres

Writing

Long-form posts at invasikode.com and dev.to

Hiring for an AI engineering role, or need a model turned into a product?