Balázs Csorba · Senior engineer for AI code & legacy modernisation
I make AI-generated code and legacy systems production-ready – without a big bang.
Coding agents ship in days what used to take a team months – but rarely production-ready. I audit, test and refactor AI-generated code and grown legacy systems while they keep running: tests as a safety net, CI gates and human review on every change. As a contractor or as an employee.
See case studiesBased in Styria, Austria · remote across Europe & the UK
500,000+
products migrated to a PIM
15+
AI agent skills I've built
19
projects in my references
Sound familiar?
When the prototype meets real users
AI tools get you to a first version fast. Real load, real data and the first security review show what was left behind.
- 01
Nobody dares to touch it
A module no one understands any more – every change is a risk, so it never happens.
- 02
Every fix breaks something else
Without tests, bugs show up in production. What should take a day takes a week.
- 03
Gaps nobody sees
Open API endpoints, missing permission checks, secrets in the repository – the usual traces of unreviewed AI code.
- 04
Slow as soon as it matters
N+1 queries, no caching, the same logic in ten variants – invisible in the demo, expensive under load.
- 05
Every release is manual work
No CI, no rollback, no staging – a Friday deploy becomes a dare.
- 06
Knowledge in one head – or one prompt
No docs, no recorded architecture decisions. New developers need weeks instead of days.
Where we start
A fixed-price code audit
Before anyone rebuilds anything: an honest look at your code. I review architecture, security, tests, performance and deployment, and write down what is solid, where the risks are and what to fix first.
The report is yours – even if you do not continue with me.
Request an audit- Result
- A prioritised list with severity and effort for every item
- Billing
- Fixed price, agreed up front
- Reviewed
- In-house software, agency code and apps built with Cursor, Claude Code or Copilot
How I work
Step by step instead of a big bang
Your system stays online while it gets better. Every step is small enough to roll back.
- 01
Understand
Audit, map the dependencies, sort the risks by severity – agents get me through large codebases fast, and I check every statement myself.
- 02
Secure
Characterisation tests pin down today's behaviour; CI gates and static analysis stop it from getting worse.
- 03
Rebuild
Module by module, the strangler-fig way: new parts grow next to the old ones and traffic moves over one function at a time.
- 04
Hand over
Tested pull requests, docs and architecture decisions in your repository – so your team can carry on without me.
Companies I’ve built for
Agentic engineering
AI agents that ship – with tests as the guardrail.
I don't just prompt. I build the tooling that lets coding agents work safely inside real client codebases, ticket systems and CI.
Ticket-to-PR pipelines
Agent skills that reproduce a production bug from real data, prove the root cause, fix it, add unit and Playwright tests and open the pull request.
Guardrails, not vibes
Tests, static analysis and CI gates decide what ships – and every change still goes through human review.
- agent run bug-fix --ticket "Order total wrong after coupon"
- reproducesynced DB + logs · failing request replayed
- root causeproved with data · query + diff attached
- jiraticket created via MCP · acceptance criteria set
- branchhotfix/<ticket> from master
- fixpatch applied · reviewed diff
- testsunit ✓ · Playwright E2E ✓ · negative check ✓
- gatePHPUnit + PHPStan green
- propened → master · waiting for human review
- # the agent does the legwork, a human (me) signs off
Services
Where I create value for your business
Three areas where companies bring me in – each measured by results, not by lines of code.
- 01
AI agents & LLM integration
AI agents and MCP servers on your own data – automating support, content and development work, measured against clear KPIs.
Learn more: AI agents & LLM integration - 02
B2B commerce & integrations
B2B shops, product configurators and customer portals on Spryker, Pimcore and TYPO3 – wired into SAP and Infor, so orders, prices and stock stay in sync.
Learn more: B2B commerce & integrations - 03
Fast, maintainable front ends
Vue, Nuxt, React and Next.js applications that load fast, rank well, meet accessibility rules and stay maintainable for years.
Learn more: Fast, maintainable front ends
Two ways to work with me
One senior engineer with AI instead of a whole team
Coding agents have changed the economics of software delivery. Concept, development, testing, integration and operations – for many roadmaps, work that needed an agency or a team of developers a year ago, I can now deliver on my own, with data protection built in. You choose the model that fits your company.
Path 01 · Contractor
Replace your agency
For companies that buy development and AI projects from agencies today.
You get the output of an agency without the typical agency overhead: no account managers, no hand-offs between sales, project management and developers, no change-request markups. One contract, one accountable senior – from the first spec to production.
- Fixed-price milestones, daily rate or monthly retainer – budgets you can plan
- A written proposal with scope and price
- NDA and a data processing agreement under Art. 28 GDPR as standard – AI providers only as sub-processors you approve
- Exclusive rights of use to everything built for you (open-source parts under their own licences) – no lock-in
Path 02 · Employee
Hire one instead of a team
For companies that want AI expertise in-house for the long term.
Instead of recruiting, onboarding and managing a whole development team, you hire one Senior AI Engineer who works with coding agents. The knowledge, the tooling and your AI governance stay inside your company.
- Full-time – for employers across Europe and the UK, remote from Austria or hybrid in Styria
- Rolls out your enterprise AI toolchain – SSO and audit logs, with GDPR and EU AI Act requirements taken into account from day one
- Makes your existing team productive with coding agents
- No recruiter fee – and a work sample on a realistic problem from your domain before you decide
The financial case
What a year of delivery really costs
The same roadmap, staffed three ways. Estimated annual costs for a mid-sized company in Austria and Germany.
Agency team
€480,000–960,000per year
Project lead, 2–3 developers, QA – 3–4 FTE at €800–1,200 per person-day
In-house development team
€250,000–510,000per year
3–4 developers incl. 20–30% employer costs, plus recruiting fees in year one
One Senior AI Engineer
By agreement
Far below both alternatives
One senior plus an enterprise AI subscription – priced to your scope after a short call
1
accountable senior instead of a team of three to four
€0
recruiter fees, agency markups and change-request surcharges
How the numbers are calculated
Own estimates based on typical market rates in Austria and Germany, 2026: agency rates of €800–1,200 per person-day for 3–4 FTE at 200 billable days; salaries of €60,000–80,000 gross for 3–4 developers plus 20–30% employer costs; recruiting fees of 20–30% of an annual salary. My fee is agreed individually; even with the enterprise AI subscription it stays well below both alternatives. The comparison assumes comparable delivered output – which you check on a real task before you commit. As a contractor, you pay for agreed deliverables or booked days instead of a salary – with no employer costs, no recruiting fees and no long-term commitment.
Why it holds up in a mid-sized or large company
Data protection by design
AI tooling only in the setup you approve – an enterprise plan under commercial terms: no training on your code or data, a data processing agreement with the provider, configurable retention. Where data must not leave the EU or your network, the AI I build for you runs in EU cloud regions or on-premise.
No single point of failure
Tests, CI, documentation and runbooks live in your repository, so your team or a successor can take over at any time.
Prepared for approval
Technical documentation for your EU AI Act risk assessment, audit logs and role-based access – the basis IT security, your legal team and the works council need for their review and a works agreement.
FAQ
What teams ask before we start
Do you refactor or rebuild?
Mostly I refactor. The AI often got the structure roughly right; the problems sit in edge cases and missing safeguards. Where a part cannot be saved, I rebuild it and document why.
Do you review code from Cursor, Claude Code or Copilot?
Yes – that is the core of my work. I use coding agents every day myself and know their typical failure patterns.
Does the system have to stop?
No. Changes go live in small, tested steps, and each one can be rolled back.
What happens to our code and data?
I work in your repository and your infrastructure, with AI setups designed for the GDPR and no training on your data. An NDA is a given.
Which stacks?
PHP (TYPO3, Symfony, Spryker, Pimcore), TypeScript (Vue, Nuxt, React, Next.js, Node), Python and Go. With coding agents, a new stack is rarely a blocker.
Contractor or employee?
Both. As a contractor for an audit or a clearly scoped rebuild – or on your team, when AI code and legacy systems are a permanent topic. Remote across DACH, Europe and the UK, or hybrid in Styria.
Contact
A codebase nobody wants to touch any more?
Tell me about your project or the role you want to fill, and we’ll see together whether I’m the right fit.