Skip to content
View katulevskiy's full-sized avatar
🤍
🤍
  • Unlimited Limited
  • San Diego

Highlights

  • Pro

Block or report katulevskiy

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
katulevskiy/README.md
Daniil Katulevskiy — GPU-accelerated AI systems engineer

Email GitHub CV

 

Featured Projects

Custom Game Engine + Multiplayer 3D FPS

▸   Vulkan · DX12 · Metal cross-platform

C++ SDL3 Vulkan DirectX 12 Metal

C++ engine on SDL3 / SDL_GPU dispatching natively to Vulkan, DirectX 12, and Metal. Authoritative netcode with client prediction + lag compensation. PBR, cascaded shadow maps, GTAO, SSR, volumetric lighting, SMAA T2x.

GPU Kernel Optimization · CUDA / OpenCL BLAS

▸   85 % of cuBLAS SGEMM on RTX 4090

CUDA OpenCL Nsight

Dense GEMM with shared-memory tiling, warp-shuffle reductions, and register micro-tiling. Nsight + roofline analysis on RTX 3090 / 4090.

Multi-Region GPU Inference Cluster

▸   Self-hosted Kubernetes, 6 GPUs, multi-site

Kubernetes vLLM LoRA Prometheus

Bare-metal Kubernetes across multiple sites for vLLM serving + LoRA finetuning experiments. Prometheus / Grafana telemetry.

Post-Quantum Encrypted Messaging

▸   Kyber-1024 + X3DH + Double Ratchet

Go TypeScript Electron

E2E encrypted chat with identifier-free relays + custom anti-DPI TLS obfuscation. Go backend, TypeScript / React / Electron client.

 

Experience

▸   Upgrading fintech infrastructure at Polity Network — took a single-EC2 monolith to a real AWS EKS cluster with OpenTofu + ArgoCD. Ephemeral per-PR review environments cut the release cycle ~40 %.

▸   Bringing Google Pixel SoCs up over PXE for a 20,000-phone datacenter at UCSD × Google. Living in the bootloader / kernel layer — UART debug, porting Android kernel modules into mainline Linux.

 

Tech Stack

LANGUAGES
GPU / HPC
AI / ML
INFRA
SECURITY

 

Contact

Currently open to GPU systems, ML infrastructure, and high-performance engineering roles for new-grad 2026.

▸   Email   ·   dkatulevskiy@gmail.com

▸   GitHub   ·   github.com/Katulevskiy

▸   Resume   ·   Daniil Katulevskiy CV.pdf →

✦

Popular repositories Loading

  1. tech_layoffs_ml tech_layoffs_ml Public

    Using machine learning to predict layoffs in tech companies

    Jupyter Notebook 6 3

  2. LAYOFF-PREDICTION LAYOFF-PREDICTION Public

    Machine learning model used to predict layoffs in different comanies within technical sector using financial and statistical data.

    Jupyter Notebook 2 1

  3. LoLPredictions LoLPredictions Public

    Jupyter Notebook 2

  4. ACS-Android-CRM-System ACS-Android-CRM-System Public

    my Android CRM app with integration of firebase realtime DB and authentication

    Java 1

  5. path-planning-2 path-planning-2 Public

    Forked from vzaripov/path-planning

    Enhancing the initial path-planning algorithm

    Python 1

  6. cse135-fullrepo cse135-fullrepo Public

    HTML 1