// companies I worked with

// approach

Portrait of Ivan Shabanov

I own features end to end — data model, API, production UI, infrastructure, monitoring. Production AI is where I go deepest: model cascades, MCP servers wired into internal systems, agentic pre-review.

// numbers

<30 s
lead response vs an ~8-minute human average: AI assistant, channel moved fully to it
1 week
for a credit product to become profitable — a 3-person team I led
<1 s
100,000-row lead-scoring table instead of 8 s, 9K+ leads a day
2 h → 40 min
a CRUD module with tests — the AI workflow I onboarded the team on
~10×
lower API costs from the LLM model cascade I designed
58 → 87
Lighthouse Performance on the catalog under the agency's paid traffic, conversion ~1.5×
Ivan Shabanov with a “you are our greatest asset” award from the team
// recognition from the team

~/cases

What I've shipped

// about

Ivan Shabanov on a waterfront against a night city skyline

Ivan Shabanov

I led the AI lead-processing assistant that cut lead response from an 8-minute human average to under 30 seconds, and led a 3-person team that took a credit product from zero to profitable in its first week. Today I am a Senior Full-Stack Engineer on the Alfa-Dengi project at Alfa-Bank (via outsourcing partner GIDFINANCE): a cross-functional team where I ship e2e features from the backend to the interface.

roleSenior Full-Stack Engineer · TypeScript / Node.js / React
focusProduction AI: model cascades, custom MCP servers, agentic pre-review
domainFintech and lead generation: credit products, ad-traffic scoring, AI assistants
formatRemote · B2B contractor / EOR · full overlap with EU hours
experience4 years in production: SODA → Appbooster → Alfa-Bank (GIDFINANCE)
EnglishProfessional working proficiency, daily use in a distributed team

// career

From agency to fintech

2022 — 2023

SODA

remote · Aug 2022 — Oct 2023

Lead-generation agency for residential real-estate developers and law firms: ~60 employees. Owned the client-server side: APIs, database, and interfaces.

  1. 2022 — 2023

    SODA

    remote · Aug 2022 — Oct 2023

    Lead-generation agency for residential real-estate developers and law firms: ~60 employees. Owned the client-server side: APIs, database, and interfaces.

    // role

    Full-Stack Engineer

    ~/product

    AI lead-processing assistant, Node.js microservices, React integration hub, SPA sites receiving paid traffic

    achievements

    • Led the AI lead-processing assistant: lead response under 30 s vs an ~8-minute average; after a three-month humans / humans + AI / AI-only comparison the channel moved fully to the assistant — channel profitability ×3

    • Designed a cascade of LLM models: API costs cut tenfold

    • Rewrote a legacy PHP monolith into Node.js/TypeScript microservices (Express, PostgreSQL): service decomposition, migration of business logic and APIs

    • Internal React integration hub linking the agency's CRM with partner property developers' CRM systems

    • Lighthouse Performance 58 → 87 on the SPA sites receiving the agency's paid ad traffic — conversion up ~1.5×

    ReactTypeScriptNode.jsExpressPostgreSQLLLMLighthouse
  2. 2023 — 2024

    Appbooster

    contract · remote · Nov 2023 — Aug 2024

    Mobile app marketing platform: ~100 employees, 10,000+ apps promoted for clients across 26 countries.

    // role

    Full-Stack Engineer (contract)

    ~/product

    Task-and-rewards product: React dashboard, chatbot notifications, admin verification queue

    achievements

    • Grew the task-and-rewards product from a few dozen to 1,000 daily active users in 3 months — the whole cycle: a React dashboard for paid tasks and proof, chatbot notifications that bring users back, an admin verification queue

    • Every payout verifiable: the full task lifecycle from pick-up to payout — a moderation queue processing hundreds of completions a day, anti-fraud rules screening out duplicates and faked proofs

    • Ad-traffic attribution (UTM and referrer parsing) alongside activity and return-rate metrics — paid channels judged by retained active users

    ReactNode.jsExpressPostgreSQL
  3. 2024 — now

    Alfa-Bank

    Alfa-Dengi project · remote · Sep 2024 — present

    Consumer lending product in the ecosystem of one of Russia's largest private banks; delivered via outsourcing partner GIDFINANCE. Cross-functional product team; I ship e2e features from the backend to the interface.

    // role

    Senior Full-Stack Engineer

    ~/product

    Credit reports, microloan-brand showcases, push campaigns, lead scoring, events on Kafka

    achievements

    • Led a 3-person team on an end-to-end credit-report product — design, flows, API, NBKI bureau, Node.js backend, search over 6M rows; profitable in its first week: net profit +40%, EPC doubled

    • Shipped a feature adjusting microloan-brand showcases to each user's loan history — approvals up

    • Push-campaign builder (NestJS + React): marketers launch automated sends by application status without developer involvement

    • Brought Claude into the project, set up MCP servers, trained colleagues on AI agents — team productivity up

    • 100,000-row lead-scoring table (9K+ leads a day): from 8 s to under 1 s

    • Notification delivery and domain events on Apache Kafka: zero message loss at peak load

    • Devised and built the code-deployment pipeline: GitLab CI/CD into Kubernetes, OpenTelemetry tracing, Grafana alerting

    Node.jsNestJSReactKafkaKubernetesGitLab CI/CDOpenTelemetryClaude CodeMCP

[now]

The next product

The next one could be yours: I take a feature from data model to production monitoring, set the engineering standards the team works by, and onboard the team on an AI workflow — Claude Code, custom MCP servers, agentic pre-review.

get in touch →

// stack

AI Engineering

  • Claude Code
  • MCP servers
  • AI agents
  • Agentic code review
  • LLM integration
  • Model cascading & routing
  • Prompt engineering
  • AI chatbots

Frontend

  • React 18/19
  • TypeScript
  • Next.js
  • Redux Toolkit
  • Zustand
  • RTK Query
  • React Router
  • Ant Design
  • CSS Modules / Sass
  • Feature-Sliced Design
  • Vite
  • Webpack
  • Recharts

Backend

  • Node.js
  • NestJS
  • Hono
  • Express
  • PostgreSQL
  • Turso
  • Redis
  • Kafka
  • Prisma
  • Drizzle ORM
  • Zod
  • REST
  • GraphQL
  • WebSocket

Infra

  • Docker
  • Kubernetes
  • GitHub Actions
  • GitLab CI/CD
  • Sentry
  • Grafana
  • OpenTelemetry
  • Playwright
  • Vitest / Cypress
  • Jest
  • Supertest
  • nginx

// how I work with AI

I keep AI on a short leash: I design the architecture myself and take generated code apart by hand, so my brain doesn't atrophy behind the model. The whole team now runs on my workflow: a CRUD module with tests takes 40 minutes instead of 2 hours.

Production is still on me.

  • Claude Code
  • MCP servers
  • superpowers
  • Council
  • Context7
  • Obsidian
  • Chrome
I reply the same day

Looking for an engineer
who owns features end-to-end?

Drop me a couple of lines about the role and the team. CV and GitHub links are in the contact section below.

Email meSee case studies

~/contact

Let's talk