Skip to content
View AyushPramanik's full-sized avatar

Highlights

  • Pro

Block or report AyushPramanik

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
AyushPramanik/README.md

Hey, I'm Ayush

My work spans across software engineering, ML cancer research, AV software and quantitative algorithmic trading.

Pinned Loading

  1. MLH-Production-Engineering MLH-Production-Engineering Public

    Production engineering and SRE-focused infrastructure project built during the MLH Production Engineering hackathon, covering scalable backend systems, observability, Docker, CI/CD, monitoring, loa…

    Python 2

  2. QLoRA-FineTuning-Platform QLoRA-FineTuning-Platform Public

    QLoRA fine-tuning platform for LLMs with distributed training, 4-bit quantization, vLLM inference serving, Kubernetes deployment, experiment tracking, and production-grade ML infrastructure tooling.

    Python

  3. Distributed-Search-Engine Distributed-Search-Engine Public

    Production-style distributed search engine built with C++, Go, gRPC, Redis, and React featuring sharded inverted indexes, distributed query aggregation, BM25 ranking, caching, observability, and re…

    C++

  4. Distributed-Job-Queue Distributed-Job-Queue Public

    Distributed job queue with retries, visibility timeouts, dead-letter queues, and Prometheus/Grafana observability.

    Java 2

  5. CPP-Web-Server CPP-Web-Server Public

    Modern C++20 high-performance HTTP server inspired by NGINX with epoll, async I/O, threading, and production systems architecture.

    C++

  6. GPU-Cluster-Scheduler GPU-Cluster-Scheduler Public

    Distributed GPU cluster scheduler and observability platform for ML workloads, featuring resource-aware scheduling, fault tolerance, Kubernetes orchestration, and real-time cluster monitoring.

    Go