Agents in production
Tools with narrow scopes, an evaluation loop against fixtures, a cost cap, models compared between releases. No framework you cannot debug.
For recruiters, contracting agencies and teams
An AI engineer who has shipped agents to production
Node.js and TypeScript for nine years, LLM agents in production since 2024. I build the tools, the evaluation loop and the cost cap, and I review every change an agent makes. Contract or full time, from November 2026.
- “someone you can always count on”public LinkedIn recommendation
- “a true bias for action”client CTO, on LinkedIn
- 15+ yearsshipping software
- Free call, no pitch deck30 minutes, then you decide
What I bring to your team
MCP servers and integrations
Your product usable from ChatGPT and Claude, on top of your existing login, with adoption measured per client.
Coding agents under rules
CLAUDE.md and AGENTS.md, skills, hooks and CI gates. In 2026 an agent opened about 30% of my team’s merged pull requests, and I reviewed about 85% of them.
The rest of the stack
React and Next.js, Node.js, PostgreSQL, Cloudflare Workers, PostHog. I ship the whole feature, from the database to the screen.
Terms
Contract (B2B)
150 to 200 PLN an hour (45 to 55 USD), invoiced from Poland. Full time or a fixed number of days a week.
Employment
Open to a full-time role as an AI engineer or AI enablement lead. Salary to agree on the call.
Start
November 2026. Remote from Wrocław (CET), office days by arrangement.
Process
A 30-minute call, a technical conversation with your team, and I am happy to do a paid trial task instead of homework.
Setting up a team of AI builders?
- If your company is starting a department where people build tools with Claude Code, Codex and n8n, I can set it up and run it: shared rules, review, deployment, costs.
- Your people keep building; I keep the quality bar and the bills under control.
Proof
Fifteen years of shipping software, 25+ apps with 3.7M+ downloads, founding engineer at a SaaS shipped on eight platforms. The work below is described with numbers; client names stay private.
An AI coding agent as a team member, under enforced rules
- The problem
- Coding agents produce ten times the output and ten times the mess. A team of four wanted the speed without a slop swamp on main.
- What I did
- I authored the rule set shared by Claude Code and Codex: mechanical checks over written rules, lint and test gates for security, API surface and CSP, agents working on main with hooks, every PR reviewed by a human, AI-assisted content disclosed as such.
- Result
- In 2026 the agent opened about 30% of merged pull requests across two products and I reviewed about 85% of them. My own output went from under 1,000 to 5,000+ commits a year.
See also: AI & agents · Full-stack & custom software
An MCP server from first merge to first external users
- The problem
- Users wanted to log time from their AI assistants. The API existed, the agent surface did not.
- What I did
- I set the tool surface, removed destructive tools, routed every operation through the existing REST controllers so an agent gets no wider access than a person, and instrumented adoption per client in PostHog from day one.
- Result
- First external users within weeks. A bot-protection rule that rejected MCP clients by user agent was found and removed the same day because the dashboard showed it.
See also: AI & agents · PostHog & product analytics
Agentic content platform built from scratch, quality measured not assumed
- The problem
- Thousands of articles were needed, with AI disclosure built in and without publishing slop.
- What I did
- Late 2024 I built the agent driver: enforced stop conditions, tool-call limits, parallelization, delegation chains. Quality came from best-of-n, LLM-as-judge, scoring against fixtures and plagiarism checks, with many models evaluated across their releases.
- Result
- Thousands of articles shipped through the platform. Content deployed automatically across 300+ generated sites with git-backed bulk operations and reputation monitoring.
See also: AI & agents · AI in your company
An AI engineer who has shipped agents to production
Senior AI engineer from Poland: Node.js and TypeScript, LLM agents in production, MCP servers, evals and cost caps. B2B contract at 150 to 200 PLN an hour or full-time employment, from November 2026, remote from Wrocław.
FAQ
Questions
Are you available for a full-time role?
Yes, from November 2026, as an AI engineer or AI enablement lead. B2B contracts work too.
What is your rate?
On a B2B contract, 150 to 200 PLN an hour (45 to 55 USD). For employment, we agree on the call.
Which models do you work with?
Whatever wins the evaluation for the task: Claude, OpenAI models and open models, compared on the same fixtures.
Can I see your CV?
Yes, at ciunkos.com/resume.
Let’s find out in 30 minutes
A free 30-minute call. You bring the problem, I bring questions. No prices on this page because scope comes first.
If I am the wrong person I will say so on the call and point you to someone better.
or write to ciunkos@gmail.com
After you book: a calendar invite, then the call. Nothing else to fill in.
Available from November 2026 · B2B contract or employment · Wrocław, Poland (CET), remote