Skip to content
View akrisanov's full-sized avatar
👀
Looking around
👀
Looking around

Block or report akrisanov

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. 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
akrisanov/README.md

Staff Software Engineer building AI infrastructure and distributed systems.

Most recently at Severstal, I worked on a production GenAI platform running on Kubernetes and NVIDIA GPUs across multiple data centers. My work covered LLM serving, routing, GPU placement, capacity planning, reliability, observability, model rollouts, and performance tuning.

I prefer roles where I can design systems, write code, investigate production issues, and own technical decisions end to end.

Earlier in my career, I built backend and platform systems across SaaS, fintech, payments, data privacy, and high-traffic products.

I write about AI infrastructure, ML systems, and distributed systems at akrisanov.com.

Pinned Loading

  1. plans plans Public

    Portable, harness-agnostic planning and coordination for agent-driven software work.

    Python 2

  2. kubetask kubetask Public

    Kubernetes-based execution service for isolated, short-lived tasks with resource controls, artifact storage, and task lifecycle management.

    Go 1

  3. local-agent-stack local-agent-stack Public

    Local-first stack for running coding agents against shared local or remote inference.

    Python 2

  4. llm-serving-lab llm-serving-lab Public

    vLLM serving environment with GPU provisioning, workload telemetry, ClickHouse analytics, and Grafana observability.

    Python

  5. python-field-notes python-field-notes Public

    🐍 Practical examples, experiments, and reference notes for modern Python.

    Jupyter Notebook 6

  6. planfact/Reliable.HttpClient planfact/Reliable.HttpClient Public

    Production-ready HttpClient ecosystem: resilience patterns + intelligent caching + universal response handlers. Zero config, multiple approaches, seamless substitution.

    C# 9