Full-Stack Engineer

Kyiv, Ukraine

Available for work

IVANMYRONIUK

Senior Full-Stack Engineer — production AI systems. I own AI features end-to-end: retrieval, agents, evals, and the interface around them — shipped to production, not to a demo.

Get in touchLinkedIn ↗
Scroll
4.5+
years of engineering
7+
products shipped

01 / Work

Products in production

✦TypeScript✦Node.js✦NestJS✦Next.js✦RAG✦Agents✦PostgreSQL✦Elasticsearch✦AWS

02 / Companies

Where I've worked

Latest role

06/2024 — 08/2026

Kyiv

Aleph One

Full-Stack Engineer (AI)

Senior engineer across three production products — Beana AI (AI search platform), CritiqueMatch (consumer product with paid services), and an internal Calls App — owning features end-to-end from backend architecture to UI, and working directly with the client to turn feedback into scoped, shipped features. On Beana AI I drove the AI direction: retrieval and agent architecture, model selection, and the eval strategy that kept LLM quality measurable.

Beana AI · CritiqueMatch · Calls App

View role

Key impact

  • Cut AI search latency from 20+ seconds to ~3–4 seconds: profiled the retrieval and ranking path and fixed the bottlenecks (to 6–7s), then parallelized tool calling to get under 4 seconds.
  • Raised RAG pipeline accuracy from ~30% to 90%+ on QA test suites validating filters and LLM outputs.
  • Grew automated test coverage from zero to ~75% across both frontend and backend.
  • AI search running in production over a catalog of 100k+ items, serving real users daily.
All companies →Earlier: EPAM — Winter Courses, 12/2021 — 02/2022

03 / About

Beyond simple LLM wrappers

I design and ship production AI systems in JavaScript / TypeScript: RAG pipelines, agentic and multi-agent workflows, tool calling, and prompt-engineered, eval-driven LLM features on a Node.js / NestJS backend and React / Next.js frontend. Comfortable across the whole stack — from PostgreSQL, vector stores, and AWS to CI/CD, testing, and performance profiling. Mostly in startups, owning features end-to-end — including 3+ payment and monetization integrations shipped across products.

My core strength is adaptability: I pick up unfamiliar technologies fast and become productive quickly.

Latest: cut AI search latency from 20+ seconds to ~3–4 seconds on a catalog of 100k+ items — profiling and bottleneck fixes first, then parallelized tool calling.

Core

JavaScript · TypeScript · Node.js · NestJS · React · Next.js · REST API design · GraphQL · WebSockets

AI / LLM

RAG pipelines · DAG-based pipeline orchestration · Agentic & multi-agent workflows · Tool calling · Multi-turn conversations · Prompt engineering · Fine-tuning · Evals & AI harness · LangChain & LangGraph · OpenAI | Anthropic | Google SDKs · Vector stores · Image generation

Data & Infra

PostgreSQL · MongoDB · ClickHouse · MSSQL · Supabase · Elasticsearch · Redis · AWS (ECS, EC2, S3, SQS, Lambda, RDS, CloudWatch, IAM, Secrets Manager) · Terraform (IaC) · Azure · Nginx · Docker · Microservices · Stripe · Auth0 · HubSpot · Zendesk

UI

Tailwind CSS · SCSS / Sass · Styled Components · Radix · shadcn/ui · Material UI

Testing & Practices

Jest · Vitest · Playwright · Cypress · Unit & integration testing · TDD · CI/CD · Git · Turborepo · AI-assisted development (Claude)

04 / Contact

Let's talk

Open to interesting full-stack and AI engineering work. Telegram is the fastest way to reach me — or email; I usually reply within a day.

ivan.myroniuk0@gmail.com