Fullstack engineering → Generative AI
LLM applications, agents and retrieval-augmented generation, grounded in hands-on software delivery.
ELENA CHIPERI / SOFTWARE ENGINEER
Every part.
One system.
From application architecture
to useful AI.
I build software, connect the pieces and write about the decisions behind them. A decade of fullstack engineering, now applied to LLM applications, agents and RAG.
APPLICATION / SYSTEM BOUNDARY
Person[ User ]
01 / INTERFACEWeb applicationAccessible, focused experiencesTypeScript · Angular
02 / APPLICATIONApplication APIRules, boundaries, decisionsNestJS · REST
03 / PERSISTENCEDatabaseReliable stateSQL · Storage
04 / INTELLIGENCEAI workflowContext → useful outputPython · RAG · Agents
ABOUT THE PERSON BEHIND THE CODE
All articles ↗
Decisions, trade-offs and lessons from the work.
02 / TOPICSCategories ↗
Explore the bigger areas of engineering.
03 / CONNECTIONSTags ↗
Follow a technology, pattern or question.
10 yearsSoftware engineering
End to endArchitecture → delivery
GenAILLM apps · agents · RAG
View professional profile ↗01 / EXPERIENCE
The whole system.
Not just the code.
From choosing an architecture to keeping a product running, I connect technical decisions to the work they need to do.
B2B logistics · end-to-end delivery
Sole technical ownership: architecture, stack selection, infrastructure and delivery. Working toward solution architecture for distributed, event-driven and high-load systems.
More about my background ↗02 / HOW I THINK
Build with a reason.
Three connected disciplines.
One practical engineering approach.
Design the system
Start with constraints. Make architecture decisions explicit and complexity intentional.
System design / ArchitectureOwn the delivery
Connect the application, infrastructure and the decisions that keep a product maintainable.
Fullstack / InfrastructureApply intelligence
Bring agents and language models into useful workflows, with evaluation built into the process.
Generative AI / Agents / RAG03 / CONTINUOUS LEARNING
Practice, meet
perspective.
Selected programs and credentials listed on my professional profile.
View credentials on LinkedIn ↗GenAI and Agentic AI for Software Engineering
SET University
Solution Architecture Program
SET University
Microservice Architecture
Robot_dreams
EDUCATION
Ukrainian State University of Science and Technologies (USUST)
04 / CODE & TRADE-OFFS
Notes from the work.
The choices, compromises and lessons behind building software.
Software Engineering · Generative AI
LLM Generation Parameters: Decoding Method Decides
Thirteen knobs sit in a watsonx.ai generation config, and one of them silently decides whether the three most famous ones do anything at all — and it isn't temperature.
9 Sep 2026 ↗
Software Architecture · Software Engineering
I Rebuilt One App's Architecture Three Times — Here's How I Choose Now
I rewrote the architecture of a single logistics app three times, each time chasing the "best" architecture instead of the one the project actually needed — and that mistake taught me more than any bo…
23 Jun 2026 ↗
Security · Web Development
When `npm install` Becomes a Trap: The New Wave of NPM Malware
A logging library shouldn't be able to steal your AWS keys — yet that's exactly what the latest wave of npm malware is built to do, and it changed how I install.
20 Jun 2026 ↗
Software Architecture · Security
Auth0 vs Keycloak: How I Choose for Scalable Identity
The hardest part of a distributed system isn't the microservices — it's deciding who owns identity, and that's the call I see teams underestimate the most.
19 Jun 2026 ↗
Software Engineering · Web Development
Why I Keep Coming Back to Angular + NestJS + PostgreSQL
I didn't plan to fall for this stack — but a few months of shipping with Angular, NestJS, and PostgreSQL quietly turned me into a believer, and here's the honest why.
19 Jun 2026 ↗LET’S TALK