Hey! I'm

Lukas Janda

I build and ship production software — fast. A senior full-stack engineer with an AI-accelerated workflow that turns weeks of delivery into days.

I founded and led a software company — a team of ~15 engineers at peak. With a modern stack and an AI-accelerated workflow, I now deliver that same scope with 2–3 people. I've run it both ways.

~15 engineers→same scope→2–3 people

// remote · EU & US friendly · English

// what I do

  • MVP builds Fixed scope, fixed price — working software in days, not months.
  • AI integration Bringing LLMs and automation into real products, not demos.
  • Integration-heavy work Making the tools a business already runs on talk to each other.
  • Fractional tech lead Senior engineering judgment, part-time.

// how I deliver

// working software early — then tuned against real use

talk to users→requirements→sketch workflow→align→prototype→deploy→real use→tune

I talk to the people who'll actually use the thing, agree the workflow before anyone writes code, then get a functional prototype deployed and in real use as fast as possible. Everything after that is tuning against reality instead of guessing — which is why scope stays honest and nothing gets built for six months before someone notices it's wrong. Tasks and use cases get documented as I go.

// how I build

// a few things I build a lot — and how they actually work

Offline-first field apps

capture→local queue→reconcile→sync

Work is captured straight to the device and dropped onto a durable queue, so a dead connection never loses anything. When the network returns, queued events replay in order and conflicts resolve against server state — the person using it never has to think about "offline."

TypeScript · IndexedDB · service workers · REST / JWT

AI document pipelines

ingest→extract→classify→validate→report

Inbound files move through isolated serverless steps: OCR pulls the text, an LLM classifies and structures it, results are checked against reference data, and a clean report comes out the other end. Each step is retryable, so one bad input never stalls the batch.

Python · serverless · Claude API · OCR

Image detection & segmentation

image→on-device model→vision-LLM fallback→structured result

A fast on-device model locates and segments objects and text in a photo in real time; anything it's unsure about escalates to a vision-LLM for a second opinion. Raw pixels go in, structured and checkable data comes out.

YOLO · on-device CV · vision LLM · TypeScript

Automated discovery & monitoring

scan sources→filter→LLM-score→dedup→digest

A scheduled job sweeps multiple sources, cuts the noise with a keyword pass, then has an LLM score each item for fit with a short reason. Everything seen is remembered so nothing repeats, and a single ranked digest lands in your inbox each morning.

serverless cron · Claude API · KV store · email

System integrations

source API→transform→dedup + retry→destination

Scheduled services move and reshape data between internal APIs and third-party platforms — format conversion, deduplication, retries with tracking — so systems that were never meant to talk stay in sync without anyone babysitting them.

serverless · queues · REST / SOAP · webhooks

// also: document & PDF generation · data-import pipelines · legacy API gateways · admin dashboards

// how I work

  • -Remote and async-first — EU & US timezone friendly, in English.
  • -~10–20 hours a week, alongside a senior full-time role.
  • -Direct and low-overhead — you talk to the person doing the work.

Say hey

Got something you want built? Let's talk it through.

→hey@lukasjanda.com

// usually replies the same day