Skip to content
View Divaaaan's full-sized avatar

Organizations

@alpes-it

Block or report Divaaaan

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.

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
Divaaaan/README.md

Danya — full-stack & ML engineer

WHOAMI

Full-stack & ML engineer. I build production systems end-to-end — backend, frontend, and the infrastructure under them — and I work AI-native: LLM agents, MCP tooling, local models.

STACK

Python FastAPI Django TypeScript React Go Rust PostgreSQL Docker Linux

FEATURED

repo what it is stack status
procurement-forecasting demand forecasting built around the ordering decision — quantile-of-sum orders, tiered service levels, order-level backtesting; benchmarked on M5 Python · Nixtla · LightGBM v1
tenebra cross-platform VPN client on sing-box — stdlib-only core, honest leak-check, CI with race detector + e2e Go · Tauri · React pre-release
Dota AI Coach real-time coaching over Valve's official GSI — deterministic rule engine + LLM advice on a transparent overlay Python · FastAPI · Electron early

CURRENTLY

  • applied ML — demand forecasting on the Nixtla stack: demand classification, conformal prediction intervals, hierarchical reconciliation, honest leak-free backtesting
  • LLM tooling — real-time agents, MCP integrations, local-model pipelines

SIGNALS

Language distribution and contribution stats

CONTACT

Email

Pinned Loading

  1. proj_d proj_d Public

    Live AI coach for Dota 2 via official GSI: FastAPI listener + transparent Electron overlay

    Python

  2. tenebra tenebra Public

    Cross-platform VPN client built on sing-box

    Go

  3. procurement-forecasting procurement-forecasting Public

    Procurement-oriented demand forecasting for many-SKU intermittent demand: quantile-of-sum ordering, tiered service levels, order-level backtesting. Demonstrated on M5.

    Python