Skip to content
View kiriloman's full-sized avatar

Block or report kiriloman

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
kiriloman/README.md

Hi, I'm Kyrylo 👋

I am a Senior Software Engineer and architect focused on building intelligent infrastructure systems, cloud cost-optimization tools, and scalable AI platforms.

Currently, I'm anchoring the technical vision and architecture for Kimchi, an AI infrastructure platform that scaled from an internal initiative to its own standalone brand.

🛠️ What I Do

  • AI & ML Infrastructure: Developing performance-critical AI harnesses, prompt-routing mechanics, and LLM cost-optimization layers.
  • Cloud & Kubernetes Systems: Writing low-level scheduler overrides, managing multi-cluster topologies, and automating infrastructure via IaC.
  • Distributed Services: Architecting high-throughput, low-latency data streaming components and backend engines (primarily in Go).

📜 Patents & Research

I hold patents focused on making cloud infrastructure and LLM orchestration significantly more efficient:

  • Automated Selection of LLMs in Cloud Environments (US12236193B1) - Intelligent, cost-efficient prompt routing across models.
  • Kubernetes Cost Optimization via Scheduler Override - Real-time data streaming component to dynamically bypass scheduler decisions.
  • 4 other patents in review.

📬 Connect with Me

Pinned Loading

  1. getkimchi/kimchi getkimchi/kimchi Public

    Terminal coding agent powered by Kimchi's multi-model orchestration

    TypeScript 665 46

  2. Multitape-Non-Deterministic-Turing-Machine Multitape-Non-Deterministic-Turing-Machine Public

    An accept-state seeking multitape non deterministic Turing machine.

    Java 18 8

  3. vllm-project/vllm vllm-project/vllm Public

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Python 82.7k 18k

  4. BerriAI/litellm BerriAI/litellm Public

    Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

    Python 50.1k 8.8k