I build backend systems and integrations that still work after launch.
I take rough briefs and turn them into services: APIs, integrations, automation, and LLM features.
Open to remote or hybrid full-time roles, plus selective contract work on difficult integrations.
Production backend, integrations, automation, and applied AI work.
Built a live catalog for model research and comparison.
I build systems teams can scale and keep running.
Featured projects
Case studies told as problem -> decision -> outcome.
nnzen model catalog
A live catalog with 500+ model cards that makes model research less scattered.
One place for the numbers that matter.
You do not have to assemble the picture by hand.
Problem: Model data was spread across different sources, so pricing, context size, limits, and quality signals had to be checked by hand.
Impact: Model choice went from tab-hopping to one place.
Custom Agent Core with MCP
LLM core with a plugin execution layer for a developer assistant: hot reload, tool chains, and explicit context handoff.
Plugins can evolve without resetting the whole assistant.
This is a durable execution layer, not a one-off demo.
Problem: Once an assistant gets more capable, plugins become hard to evolve and orchestration gets brittle.
Impact: The result is a reusable core that can support new workflows and tools without a full rewrite.
Trading Automation for an In-Game Marketplace
Automation for a constrained external marketplace with strategy logic, execution control, and logging.
Trade execution goes through service logic, not brittle UI automation.
The point is controlled execution, logging, and strategy, not automation tricks.
Problem: The platform was unstable enough that naive scripts failed quickly.
Impact: The system could keep running under platform changes instead of falling apart.
Resilient Data Collection Tooling
Data extraction tooling for a changing web environment with persistent anti-bot friction.
Reliability comes from understanding the request flow.
Stability improved through network and JavaScript analysis, not endless retries.
Problem: Standard collection approaches kept breaking because of page drift, client-side logic, and defensive mechanisms.
Impact: Less firefighting, more predictable extraction.
My primary profile
Open to Python backend roles with ownership of service architecture, integrations, and stable production delivery.
Core focus: Python backend with strong integration and operations ownership.
- Comfortable with self-hosted Linux servers, Dockerized delivery, and Caddy / Nginx style deployment paths.
- I keep infra choices practical: mostly self-hosted delivery with clear operational ownership.
Experience
Experience is organized as problem, decision, and result: what was risky, what choice I made, and what changed after release.
Backend / Integration Engineer
Freelance
Contract · delivery ownership
Build backend, integration, and automation systems for real operating workflows across external APIs, process automation, and AI-assisted features.
- Turn ambiguous requirements into maintainable services with explicit API contracts and support boundaries.
- Design integrations for unreliable external systems with robust error handling, retries, logging, and observability.
- Use reusable modules and integration patterns to shorten delivery time across new workflows.
Independent R&D Engineer
Independent projects / R&D
Self-directed research
Built focused backend and AI R&D between contracts, validating architecture patterns before using them in production-facing work.
- Validated RAG and tool-calling patterns on working prototypes before client use.
- Shifted from one-off scripts to reusable service components with clear interfaces.
- Built a practical base that later fed applied AI and AI tooling projects.
R&D Data Collection Engineer
Bright Data
Full-time
Built and maintained data-collection tooling in a changing web environment: HTTP/JavaScript analysis, resilient request flows, and fast adaptation.
- Analyzed unstable request chains and turned them into more resilient extraction logic.
- Maintained extraction quality as anti-bot controls and page structure shifted.
- Worked at the intersection of reverse engineering, reliability, and delivery speed.
Python Developer
Freelance
Contract
Built Python tools, parsers, and automation for internal workflows with messy inputs and changing requirements.
- Automated repetitive operations and reduced manual effort in data-heavy processes.
- Built service utilities and parsers for unstable integrations.
- Shipped practical Python tools quickly and stabilized them for ongoing use.
Approach
I do my best work in messy environments: unstable external APIs, awkward workflows, and AI layers on top of real operations. The goal is to make delivery predictable and supportable.
- Python backends with clear API contracts
- Integrations and automation for unreliable external systems
- Applied AI features (LLM APIs, RAG, tool calling) that fit the workflow
- Observability, debugging, and support after launch
I start with external systems, data shape, operational risk, and support cost.
I prefer systems where data flow and failure boundaries are obvious.
A solution is ready when people can monitor it, debug it, and extend it safely.
Good backend work removes manual steps and makes the next release cheaper.
The work around the work
Outside direct delivery, I keep thinking about tooling, research workflows, and the user side of engineering systems.
nnzen.com
A product experiment at the intersection of AI research and developer UX.
Agent tooling
Exploring tool-calling ergonomics, MCP, and execution loops for developer assistants.
Case-driven storytelling
I prefer showing engineering through problem -> decision -> outcome, not through a wall of stack logos.
- observability for AI workflows
- developer-facing interfaces for complex systems
- how to make AI tooling both fast and predictable
Ask about the work behind the portfolio
If you'd rather ask directly, the assistant answers from public case studies and the decisions behind them.
Open AI chatHave a messy brief? Let's turn it into a working system.
I'm a good fit when the brief is fuzzy, the systems are real, and the result has to survive production.
Remote or hybrid. Open to full-time roles and selective contract work.