Богдан

BOHDAN HAVRYLIUK
Full Stack AI Engineer • AI Automation • Backend • LLM Systems
[відкрити контакти](див. вище в блоці «контактна інформація») | [відкрити контакти](див. вище в блоці «контактна інформація») | Leicester, UK | [відкрити контакти](див. вище в блоці «контактна інформація») | github.com/bogdan734
Profile
Full Stack AI Engineer with 5+ years of software engineering experience and 4+ years of hands-on AI development, model evaluation, and AI-enabled product delivery. Experienced in building end-to-end systems across async Python, .NET, LLM integrations, backend APIs, databases, cloud deployment, and voice AI. Built and support production automation used by real recruiters and candidates. Currently founder and sole engineer of Kalorad, a self-hosted AI platform running on a model I trained myself. Final-year BSc Artificial Intelligence student at De Montfort University, Leicester (Student visa, up to 20 hours/week during term); available full-time from 2027. Seeking remote roles across England or hybrid in Edinburgh/Scotland.
Key Skills
• Languages: Python, C#, C++, C, TypeScript, JavaScript, Swift, PHP, Lua, SQL, HTML/CSS
• AI / LLM: Claude API, LLM tool use, prompt engineering, AI response evaluation, RLHF / AI training pipelines, NLP, computer vision, voice AI, PyTorch, LLM pretraining & fine-tuning, self-hosted inference, RAG
• Backend & Infrastructure: FastAPI, asyncio, SQLAlchemy 2, Alembic, Pydantic, .NET / ASP.NET, Node.js, PostgreSQL, SQLite, Redis, Docker, Docker Compose, Caddy, VPS
• Integrations: Vapi, Deepgram, ElevenLabs, SIP, Telegram MTProto / Telethon, KeyCRM REST, webhooks, REST APIs, S3-compatible storage
• Languages Spoken: English (fluent), Ukrainian (native), Russian (native)
Experience
Founder & AI Engineer — Kalorad
May 2026 – Present (Own product)
• Built a sovereign AI SaaS end to end as the sole engineer: trained a 683M-parameter decoder-only LLM from scratch (13.1B tokens, 43 GPU-hours on a single AMD MI300X, ~$86) on a self-built trilingual (Ukrainian/Russian/English) + code corpus with quality filtering and MinHash dedup; found and fixed 9 training bugs, each with a regression test. Research-stage checkpoint, 1.24B production run planned.
• Developed the platform on ASP.NET Core 9: streaming chat, RAG with cite-or-abstain, decaying long-term memory, a permissioned tool router, 20 vertical agent packs, an OpenAI-compatible public API, and a daily self-training loop (automatic scoring, checkpoint promotion, rollback on regression).
• Implemented monetisation with Stripe (subscriptions, one-off SKUs, usage metering) plus a gamified loyalty layer whose unit economics are modelled and reproducible in Python.
• Shipped growth infrastructure: Telegram bot integration, push chains, a referral loop with anti-abuse trust levels, and an admin analytics dashboard.
• Ran two security reviews and fixed real issues: CSRF across 33 of 37 POST endpoints, a stored XSS, a plugin-CSS script-injection path, and critical/high-severity vulnerable NuGet dependencies. Added a site-wide CSP, rate limiting, account lockout, TOTP two-factor login with recovery codes, email verification, password reset and cross-device session revocation.
• Covered the system with 485+ executable smoke and end-to-end checks (web, API, agents, bots, privacy, config) run on every build.
• Prepared investor and grant materials (pitch decks, technical overview, financial model) and applications to programmes including EBRD Star Venture and Hub71; running pilot and partner conversations.
AI Engineer / AI Programmer (contract) — STL
Aug 2026 – Present (Part-time freelance, contract basis)
• Engaged as a contracted specialist (official contract title: Engineer-Programmer / AI Engineer / AI Programmer) to develop a computer-vision system for vehicle identification from photographs.
• Building a detection and OCR pipeline that scans vehicle photos, locates and reads license plates, and matches a queried plate number against the indexed photo set, returning ranked candidate matches (e.g. top-10).
• Added automatic make/model classification for matched vehicles.
• Delivered as an independent, part-time contract engagement alongside other work, rather than in-house full-time employment.
AI Training Contractor — Scale AI
Jan 2026 – Jul 2026 (Part-time freelance, Remote)
• Evaluated AI-generated code and technical responses for correctness, helpfulness, safety, and best practices.
• Performed side-by-side comparisons across coding, algorithm analysis, and problem-solving tasks.
• Assessed time/space complexity, programming principles, and security considerations in AI outputs.
• Solved advanced Python coding exercises to validate AI capabilities and identify failure modes.
• Flagged harmful or policy-violating responses to support model quality and safety improvements.
AI Trainer — Meta
Jan 2025 – Feb 2026 (Part-time contract, Hybrid)
• Contributed to training and fine-tuning large-scale AI models through structured data generation and feedback.
• Reviewed and rated model outputs across technical and general domains to improve response quality.
• Applied software development and AI expertise to assess accuracy, usefulness, and clarity of model content.
Team Lead & Software Developer — Client under NDA
Sep 2023 – Sep 2025 (2 Years)
• Led project teams to deliver complex software and AI solutions on time and within scope.
• Coordinated task distribution and streamlined collaboration workflows across team members.
• Architected and built backend and full-stack applications using C#, .NET, Python, and SQL.
• Enforced code-quality standards and drove continuous performance optimisation.
Freelance Full Stack AI Engineer — Self-employed
2021 – Present (ongoing private-client work, alongside the roles above)
• Designed and delivered full-stack, backend, and AI automation solutions for private clients, from requirements and UX through development, delivery, and support.
• Built production applications using Python, C#, .NET / ASP.NET, JavaScript / Node.js, SQL and PostgreSQL, REST APIs, Docker, and responsive UI/UX workflows.
• Built scalable business logic, integrated relational databases, and maintained high code standards across diverse technology stacks.
• Delivered several non-disclosable professional projects under NDA.
Production Projects
AI Voice Recruiter "EVA" — End-to-End Hiring Automation (Python, FastAPI, Claude API, Vapi, PostgreSQL)
• Sole developer of a production system for Kozyr Trans that autonomously calls candidates in Ukrainian, runs structured screening, and routes qualified candidates to recruiters; processed 300+ live calls.
• Integrated KeyCRM end to end: candidate cards are created and moved through the funnel automatically with transcript, call recording, AI summary, and structured screening fields.
• Built a Telegram MTProto follow-up agent for unreachable candidates, merging voice and chat dialogs into the same CRM card with deduplication.
• Implemented async services with FastAPI, SQLAlchemy 2, Alembic, PostgreSQL, Claude API, Vapi, Deepgram, ElevenLabs, SIP, webhooks, Docker Compose, Caddy, and APScheduler.
• AI Support Automation for a Payment-Processing Company
AI Support Automation for a Payment-Processing Company (Python, Telethon, pytest) (Sep 2026 – Present)
• Built a Telegram ingestion and analytics pipeline over 40,850 messages in 87 merchant and trader support groups (60 days); measured that 49% of client turns waited longer than a 15-minute SLA (median first reply 13 min, p90 3 h).
• Designed an intent taxonomy and rule engine (89% of merchant requests classified automatically; 91% / 87% precision on 510 hand-labelled messages), an SLA watchdog, shadow-mode replay comparing rule replies with human answers, and PII masking for all data leaving the machine.
AI Freight-Forwarding CRM — Kozyr Trans (architecture and delivery plan; planning stage)
• Designed a 3-month plan for a custom CRM in which AI agents take a request from first message to agreed terms with both sides, contact a base of 8–9k carriers over Viber, Telegram and WhatsApp, and leave managers only payment and document checks.
• Specified hot-swappable ports/adapters for channels, LLM and telephony, a Telegram Mini App, analytics (conversion, ROI, average check, AI spend) and a one-off Bitrix data migration.
Kozyr Trans — Corporate Website / Landing Page Redesign (in progress)
• Rebuilding the public landing page of Kozyr Trans, a Ukrainian freight carrier, to replace a 703 KB Tilda page: hero route/weight calculator, fleet picker, case photos and a scroll-driven route map.
• Python backend routes every lead through a single delivery seam; AI screening questions on the thank-you page feed the lead card; pytest tests and automated site audits.
Selected Full-Stack Projects
Personal Blueprint — AI Numerology Report SaaS (Python, FastAPI, Claude, Jinja2, SMTP)
• Built a full-stack solo SaaS flow from landing page and checkout through deterministic date-of-birth calculations, Claude-generated personalized reports, branded HTML/PDF rendering, and email delivery.
• Implemented signature-verified payment webhooks, a 208-block knowledge base, prompt guardrails and linting, an optional PDF pipeline, and 34 offline pytest tests.
Nexus — SaaS Licensing & Secure Script Delivery Platform (ASP.NET Core, PostgreSQL, Redis, Avalonia)
• Built a personal SaaS project for hardware-bound license activation and AES-256 encrypted script delivery.
• Implemented PostgreSQL/Supabase persistence, Redis caching and rate limiting, Paddle subscription webhooks, and a cross-platform Avalonia desktop client.
dZENcode Comments SPA (Django, DRF, Channels, Celery, RabbitMQ, PostgreSQL, Redis, Elasticsearch, Vue 3)
• Built a Dockerized cascading-comments SPA with unlimited reply depth, CAPTCHA, attachments, JWT auth, real-time WebSocket updates, live preview, validation, and XSS/SQLi protections.
• Designed scale-ready backend features: GraphQL, async search indexing, idempotency middleware, rate limiting, S3/CDN attachment support, Prometheus metrics, read-replica routing, partitioning template, and Locust load tests.
brain.com.ua Product Parsers (Python, Django, PostgreSQL, Requests/BS4, Selenium, Playwright)
• Built three independent parsers (Requests + BS4, Selenium, Playwright) collecting the same 12 product fields into one Django/PostgreSQL model via get_or_create, with CSV export, Docker Compose and a mode that attaches to a running Chrome session.
• Verified all three parsers against the live site and documented XPath maps and a setup guide.
scraper-starter — Scraping Project Generator (Python, Django, PostgreSQL, Docker, uv)
• Wrote a stdlib-only CLI that generates a ready, verified Django + PostgreSQL scraping project in the company layout from a single URL in about 35 seconds, replacing a 5–10 minute manual setup.
• Added a data-quality report template (fill rate, duplicates, statuses), tests and CI.
E-Trading Research Framework — Backtesting & Validation (Python, pandas, statistics)
• Built a research framework that validates crypto strategies out of sample: probabilistic and deflated Sharpe ratios, block bootstrap, a trial log (105 tests) that raises the bar for every new test, a sealed lock-box period and a survivorship-bias-free Binance universe.
• Showed that a pilot strategy's edge was a simulation artifact (profit factor 1.45 → 0.55 under realistic limit-order fills) and that most new candidates failed; found that an implied-volatility index beat realised-volatility forecasts (QLIKE −23% on BTC, Diebold–Mariano test). Paper trading only, no real money.
Telegram Mini Games Hub (React, TypeScript, Vite, grammY)
• Built a Telegram Mini App with two tower-defence games, unit-tested game engines (vitest), Telegram CloudStorage for high scores and CI/CD to GitHub Pages.
Konspekt — Lecture-to-Notes iOS App (Swift 6, iOS)
• Built a native iOS app that records lectures and turns them into structured study notes, with a tested Swift package and a content pipeline covering anatomy, chemistry, Latin, English and history.
University Projects
AI Conversational Chatbot (Python, NLP, REST API)
• Built a context-aware chatbot with NLP preprocessing, intent recognition, entity extraction, and a REST API layer for external applications.
Rice Variety Classification via Transfer Learning (MATLAB, AlexNet / GoogLeNet)
• Applied transfer learning, data augmentation, stratified splits, SGDM fine-tuning, and accuracy/confusion-matrix evaluation.
Education
BSc (Hons) Artificial Intelligence — De Montfort University, Leicester
2023 – 2027 (final year)
• Core modules: Machine Learning, Neural Networks, Computer Vision, Intelligent Systems, Data Structures & Algorithms, Software Engineering.
• Current Average: First Class Honours (71.7%).