Skip to content
View GoXChief's full-sized avatar

Block or report GoXChief

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
GoXChief/README.md

Hi, I'm GoXChief 👋

ML / Backend Engineer — I build and ship AI-powered products end-to-end: from data and models to App Store releases and production servers under real load.

What I do

  • 🤖 LLM in production — built an AI support agent that autonomously resolves customer tickets in a live CRM (RAG over a curated knowledge base, escalation logic, auto-close, safety rails). Running 24/7 with real customers.
  • 📱 Multi-platform products — iOS, Android, macOS (Catalyst), tvOS, Windows. Shipped apps through App Store / TestFlight / Google Play review pipelines.
  • ⚙️ Backend & infra — FastAPI, PostgreSQL/TimescaleDB, nginx, high-load networking (custom VPN protocols, REALITY/xhttp transports), payment integrations, monitoring.
  • 🧰 Automation — Telegram bots ecosystem (sales, support, delivery), ops tooling, ship scripts.

Featured work

Project What it is Stack
llm-support-agent Production LLM agent for customer support (closed source, architecture write-up) Python, RAG, FastAPI
rag-eval-toolkit Open-source toolkit for evaluating RAG answers with LLM-as-judge Python
vpn-platform Consumer VPN across 5 platforms: custom tunnel engines, own control plane (closed source, write-up) Swift, Kotlin, Go, Python
tg-commerce-bot Telegram sales & provisioning bot with payments and web cabinet (closed source, write-up) Python, aiogram

Currently

  • Deepening LLM engineering: fine-tuning, inference optimization, agent reliability.
  • Open to ML engineering roles in AI startups.

📫 Contact: goxchief@gmail.com

Pinned Loading

  1. llm-support-agent llm-support-agent Public

    Production LLM agent for customer support: RAG over curated KB, real actions, auto-close, escalation. Architecture write-up (source closed).

  2. rag-eval-toolkit rag-eval-toolkit Public

    Retrieval metrics (hit@k, MRR, nDCG) + LLM-as-judge answer scoring for RAG pipelines. Dependency-free, bring-your-own-model.

    Python

  3. tg-commerce-bot tg-commerce-bot Public

    Telegram sales & provisioning system: payments, idempotent webhooks, auto-provisioning, ops tooling. Architecture write-up (source closed).

  4. vpn-platform vpn-platform Public

    Consumer VPN shipped on iOS, Android, macOS, tvOS and Windows: custom tunnel engines, own control plane. Engineering write-up (source closed).