Ihor

kossflow

Ihor Kostyniuk
Senior AI Automation Engineer | LLM Agents & Orchestration, MCP, RAG, Voice AI

Senior AI Automation Engineer, 3+ years shipping production LLM systems on self-hosted
infrastructure. I built a 7-channel conversational AI support platform and AI video pipelines for 22
YouTube creators and 20+ client channels (45-65 minute films at $22-33 each in compute), and I run
10+ production applications of my own. I write the orchestration layer myself instead of adopting a
framework: tool-calling loops, custom MCP servers, multi-provider routing with automatic fallback,
checkpointed pipelines that resume after a crash, human-in-the-loop gates, and an LLM-as-judge eval
and regression harness. I ship end to end: multi-tenant SaaS, native Android and desktop applications,
AI video pipelines, and recruiting systems built to EU AI Act and GDPR obligations.

EMAIL L O C AT I O N LINK

[відкрити контакти](див. вище в блоці «контактна інформація») Odesa, Ukraine [відкрити контакти](див. вище в блоці «контактна інформація»)

LINK LINK

https://t.me/koss_flow https://demo.kossflow.com

01 Experience

AI Automation Engineer OCT 2026 → PRESENT

Software development company · Full-time
• Translate client business workflows into integration architecture, reusing existing APIs and plugins where they fit instead of building
from scratch.
• Design, build and ship production integrations primarily in n8n, with custom nodes, webhooks and transformation scripts to fill the gaps.
• Integrate LLM capabilities into client products on both sides of the stack: chat interfaces, AI-assisted UX and RAG-based features.
• Run a spec-first, AI-assisted development workflow with Claude Code, reviewing and validating every generated change before it ships.
• Own integration reliability: tests, error handling, retries and edge cases.
• Lead technical presales: discovery calls, effort estimates and solution proposals for clients in North America and the EU.

AI Automation Engineer AUG 2026 → PRESENT
IT services company · Part-time

• Delivered a multi-site workflow management platform for an industrial client: per-site Kanban boards, role-based review routes, risk
scoring and benefit tracking, integrated with the Microsoft 365 stack (Entra ID SSO, SharePoint, Teams). React, Express, PostgreSQL,
Docker, Azure Pipelines, Playwright E2E.
• Delivered a geospatial site-sourcing platform across European markets: ingests public GIS services and commercial data APIs,
normalizes them into one store and produces ranked site shortlists for the investment team.
• Delivered a data residency and security assessment of a cloud SaaS product: read-only evidence collection from cloud and CDN APIs,
network traffic analysis, static analysis of client apps.
• Built an automated prospect research pipeline for outbound: public-source company analysis with an automation hypothesis and entry
points for each prospect.

Generative AI Engineer FEB 2026 → NOV 2026
YT-Wizards · Part-time

• Scaled AI video production to 22 YouTube creators and 20+ client channels by forking reusable pipeline skeletons per niche (war and
aviation history, space, finance, watches, lore, travel documentaries); many are handed over and run self-serve on the creator's own
machine or server.
• Built the orchestration behind renders that run for hours per job: checkpointed state so any stage resumes after a crash, per-step retry
with backoff, and circuit breakers around each model provider.
• Built the FFmpeg filter_complex engine that renders those 45-60 minute films (depth-map parallax, word-timed captions), and the
handover layer that moved rendering to the clients: bundled installer, deploy-key provisioning, one-click update, server-side render and
frame-level editing in the UI. Non-technical clients now run their own renders on their own hardware instead of every video going
through me.
• Delivered 45-65 minute documentaries (~235 scenes in a 45-60 minute film) at $22-33 per video in compute, with unit economics
measured from a $0.16/min budget mode up to premium tiers.
• Gated output quality with models rather than review by eye: Gemini vision identity verification on photos, text-artifact detection with
automatic regeneration on AI images, and freezedetect frame QA.

Senior AI Automation Engineer SEP 2024 → OCT 2026

Software company (B2B contract) · Part-time

• Built and ran a 7-channel conversational AI support platform (WhatsApp, Telegram, Viber, Instagram, Facebook, Web, Email) end to end:
agent design, tool calling, per-tenant Qdrant RAG, evals and deployment. Cleared Meta App Review for production messaging
permissions.
• Turned the embeddable web widget into a lead channel for the same 7-channel agent: it runs on customer sites in the host page's
language and theme, is screen-reader accessible, and writes a visitor who leaves a phone number straight into the CRM as a card plus
an outbound webhook, so leads reach downstream systems without anyone re-typing them.
• Shipped a multi-tenant AI recruiting CRM (33 database migrations, RLS on every table, subdomain-per-workspace) running ~20 AI tasks
including CV parsing, few-shot-calibrated ATS scoring, outreach generation, and vacancy parsing, fed by a 17-source job-scraping
pipeline with HMAC callbacks and IMAP ingestion.
• Implemented EU AI Act measures for high-risk recruiting AI: DPIA/DPA templates, self-serve DSAR export and erasure, human-in-the-
loop score overrides with audit trail, and a bias-monitoring dashboard (4/5 rule cohort analysis), backed by 86+ Playwright security
tests and CI/CD with smoke-tested deploys.
• Made AI provider choice a per-tenant setting: independent chat and embedding providers across three vendors, a live model catalogue
with current prices, and graceful handling when a provider drops a model an organization still has selected.

AI Automation Engineer AUG 2025 → APR 2026
PICHE, LTD · Full-time
• Audited four business functions (procurement, accounting, legal, recruitment), turned the bottlenecks into implementation specs, and
then built the systems those specs described.
• Built a custom ATS and recruitment pipeline: vacancies and candidate data from major and niche job boards land in SmartSuite as one
system of record, then CVs are parsed, candidates scored and the technical interview generated, so screening stopped being a manual
step for the recruiters.
• Architected a LegalTech document-generation system with docxtemplater and Gotenberg: contracts and management reports are
assembled from reusable templates, so drafting moved from copy-editing old documents to filling a form.
• Built the webhook-driven operations app the teams work from: task scheduling, run monitoring, work-hour tracking and operating-
expense control in one view, so schedules and spend came out of the system instead of being assembled by hand for each report.
• Ran the infrastructure under all of it: Docker on VPS with n8n, OpenClaw agents and shared internal libraries, with uptime monitoring and
error tracking wired into every automation, so a broken flow raised an alert instead of being found by the team that depended on it.

AI Automation Engineer SEP 2023 → PRESENT

KossFlow · Self-employed
• Operate 10+ production applications on a self-hosted VPS: Next.js, Supabase, Docker Compose, Caddy, centralised monitoring and
nightly backups.
• Built KossOps, a single view over 9 servers with 36 watchdogs, a dead-man switch that reports when the monitor itself dies, and a
native Android client with push alerts.
• Built a self-hosted video-meeting platform on LiveKit with an in-call voice AI assistant (wake-word gated, RAG over the organisation
knowledge base), speaker-attributed transcription with an STT fallback chain (Groq Whisper, Deepgram, self-hosted), and automatic
meeting-to-specification PDF artefacts.
• Practice adversarial security engineering on my own systems: multi-agent audits found and closed a remote-code-execution chain (a
public anon key reaching a job queue executed as root) and a stored-XSS bypass using entity-obfuscated payloads and tag splitting -
neither was reported by gitleaks, semgrep or trivy, because the risk lived in the combination rather than in any single file.
• Built an on-device AI stack on Intel Arc: 21 video courses (1,300+ lessons, 170+ hours) transcribed with OpenVINO Whisper and indexed
into Qdrant (19k chunks, bge-m3) behind a custom MCP server that gives coding agents instant course knowledge, plus a voice-cloning
studio with zero-shot Russian, Ukrainian and English cloning, best-of-N generation gated by ASR accuracy and speaker-similarity
scoring, and an OpenAI-compatible TTS API.
• Run an autonomous multi-channel content system (LinkedIn, Instagram, Telegram, Threads) with a Telegram approval bot, 18-source
deep fact-checking, cross-model verdict verification (GPT vs Claude), and multi-provider LLM routing with automatic fallback that keeps
daily cost near zero.
• Shipped as products rather than demos: a native Android personal-finance app (Kotlin, Jetpack Compose, agentic AI chat over the
user's own finances, entrepreneur tax calendar, Wear OS companion) released and in daily use at v5.13; Papir Desktop (Tauri 2, React
19, TypeScript strict), a fully offline PDF suite covered by 3,164 unit tests and 169 Rust tests that replaced a commercial reader in daily
use; and a self-hosted over-the-air update channel with signed artefacts that took the cable out of every Android release.

03 Skills

LLM Engineering AI Agents Agentic AI Agent Orchestration Multi-Agent Systems Multi-Step Reasoning

Tool Calling & Function Calling MCP (Model Context Protocol) Server Development

Agent Memory & Context Management Prompt Engineering & Optimization LLM Evaluation (evals)

Custom Eval Harness LLM-as-Judge Verification Regression Testing Human-in-the-Loop Systems

Retry / Circuit-Breaker / Fallback Design RAG (Retrieval-Augmented Generation) Agentic RAG

Vector Databases Qdrant pgvector Embeddings Semantic Search Conversational AI Chatbots

Voice Agents (LiveKit) Speech-to-Text (Whisper) Anthropic Claude OpenAI Google Gemini Groq

Multi-Provider Routing Python TypeScript Node.js FastAPI Next.js React PostgreSQL SQL

Supabase REST APIs Docker Linux CI/CD n8n (self-hosted, queue mode) Multi-Tenant Isolation

Row-Level Security (RLS) EU AI Act Technical Controls GDPR (DSAR / Bias Monitoring)

Spec-Driven Agent Design Context Engineering Prompt / Config Versioning

Automated Fact-Checking Pipelines Observability (Sentry / GlitchTip) OpenVINO / On-Device Inference

Text-to-Speech Zero-Shot Voice Cloning Speaker-Attributed Transcription FFmpeg filter_complex

Kotlin / Jetpack Compose Flutter Tauri 2 Ansible Caddy Playwright E2E OAuth 2.0 / JWT

AES-256-GCM Encryption (BYOK) HMAC Webhook Verification Adversarial Security Review WhatsApp Cloud API

Meta Login for Business OTA App Distribution Redis WebSockets / SSE

04 Languages

English C1 Ukrainian C2 Russian NATIVE

06 Courses

Claude Code Mastery: Basics, Web Projects & Agents
JUL 2026
Udemy | Arnold Oberleiter

Vibe Coding — Build Apps with Claude Code, Cursor, and Codex
MAY 2026
Udemy | Arnold Oberleiter

OpenClaw: Run Powerful & Autonomous AI Agents Securely
APR 2026
Udemy | Arnold Oberleiter

MCP: Building Agents with Claude, Cursor, Flowise, Python & n8n
FEB 2026
Udemy | Arnold Oberleiter

AI Voice Agents: Automation with Vapi, ElevenLabs, n8n & MCP
DEC 2025
Udemy | Arnold Oberleiter

AI Automation: Build LLM Apps & AI Agents with n8n & APIs
SEP 2025
Udemy | Arnold Oberleiter

Automation #withMake
JAN 2025
Web3nity