Skip to content
View Bhanuu01's full-sized avatar
3 followers · 6 following

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Shark

Block or report Bhanuu01

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
Bhanuu01/README.md

Bhanuja Karumuru

M.S. Computer Engineering at NYU Tandon. Incoming Software Development Engineer Intern at Amazon.

I work across ML systems, backend engineering, and applied research. Recent work includes CUDA kernel experiments on H100, production-minded NLP pipelines, and backend systems work from startup and research settings. I also worked on dysarthric speech research that led to an IEEE SPCOM 2024 paper and a journal acceptance in 2026.

Selected work

  • Fused Linear Attention: CUDA study of fused and hybrid attention kernels on H100, with profiling, correctness checks, and memory-traffic analysis.
  • Deadline Detection System: RoBERTa plus BERT NER pipeline for contract deadline extraction with MLflow, Docker, and review routing.
  • Portfolio: projects, writing, publications, and current work.

Interests

  • inference optimization and GPU systems
  • backend systems for ML products
  • practical ML infrastructure and evaluation

Links

Pinned Loading

  1. StyleSync StyleSync Public

    Two-tower recommendation system with FAISS indexing, TensorFlow Recommenders, and FastAPI serving.

    Python

  2. AI-Drievn-Layout-Aware-RTL-Optimization-Loop AI-Drievn-Layout-Aware-RTL-Optimization-Loop Public

    Hackathon workflow combining Verilator, Yosys, OpenSTA, and LLM-guided patches for RTL optimization.

    C++ 1

  3. Bhanuu01.github.io Bhanuu01.github.io Public

    Personal website with project case studies, writing, publications, and resume pages.

    HTML

  4. Datanauts-Intelligent-Deadline-Expiry-Detection Datanauts-Intelligent-Deadline-Expiry-Detection Public

    RoBERTa plus BERT NER pipeline for contract deadline extraction with MLflow, Docker, and review routing.

    Python

  5. Fused-Linear-Attention Fused-Linear-Attention Public

    Forked from JnanasreeKonda/Fused-Linear-Attention

    Python